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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making processes and procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "discrimination" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Despair
    -0.75
     Siberian
    -0.75
     Yug
    -0.65
    BOOK
    -0.64
    LOAD
    -0.64
    liness
    -0.60
    FORM
    -0.60
     Emer
    -0.59
     Seasons
    -0.58
     shorth
    -0.58
    POSITIVE LOGITS
    ount
    1.18
    onduct
    1.05
    retion
    1.01
    ornia
    1.00
    ounty
    1.00
    ussion
    1.00
    uity
    0.99
    ontent
    0.95
    uits
    0.94
    ayne
    0.93
    Act Density 0.017%

    No Known Activations