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

    Neuronpedia

    INDEX
    Explanations

    verbs related to planning, implementation, and action

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions related to change, improvement, and social awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.73
    utenberg
    -0.70
    ritz
    -0.65
     Extrem
    -0.64
    perty
    -0.64
    president
    -0.63
    ippi
    -0.62
    MSN
    -0.62
    ortium
    -0.61
    fml
    -0.60
    POSITIVE LOGITS
     alike
    1.00
     accordingly
    0.92
     thereof
    0.87
     yourselves
    0.83
    ingly
    0.81
     versa
    0.81
    ings
    0.80
     ourselves
    0.79
     THEM
    0.75
     yourself
    0.75
    Act Density 0.378%

    No Known Activations