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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'E' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     minds
    -0.70
     desk
    -0.65
     Miranda
    -0.63
     Bleach
    -0.62
     Hera
    -0.60
     surrounded
    -0.60
     formerly
    -0.59
     WB
    -0.58
     Gravity
    -0.57
     Eleven
    -0.57
    POSITIVE LOGITS
    ighty
    1.39
    verett
    1.33
    mpire
    1.31
    leanor
    1.30
    LECT
    1.30
    ighth
    1.28
    choes
    1.28
    clipse
    1.28
    tymology
    1.26
    agle
    1.26
    Act Density 0.025%

    No Known Activations