Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    lines containing special characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    empty or whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.73
     delegation
    -0.71
     Jericho
    -0.71
     disproportion
    -0.71
     booths
    -0.64
     Asheville
    -0.64
     potatoes
    -0.63
     braces
    -0.63
     destro
    -0.63
     Clarkson
    -0.62
    POSITIVE LOGITS
    Ñģ
    1.03
    ________________________________________________________________
    1.01
    ________
    1.00
    ________________
    0.99
    ********
    0.98
    --------------
    0.97
    Ë
    0.96
    Ñ
    0.96
    iced
    0.96
    Ì
    0.94
    Act Density 0.018%

    No Known Activations