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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concepts or entities being disputed or labeled with quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    references to terms that are considered "so-called" or labeled in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.83
    ibrary
    -0.80
     Rivals
    -0.79
     Rica
    -0.76
     ANGEL
    -0.75
     DRAG
    -0.71
    ADRA
    -0.71
     Larson
    -0.70
     Sparrow
    -0.69
     reservation
    -0.69
    POSITIVE LOGITS
    called
    1.09
    sized
    1.03
    historic
    0.96
    shaped
    0.94
    sounding
    0.94
    oriented
    0.91
    named
    0.90
    focused
    0.90
    eared
    0.89
    equipped
    0.89
    Act Density 0.022%

    No Known Activations