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

    Neuronpedia

    INDEX
    Explanations

    words related to things being motivated or influenced by certain factors

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "driven" related to various causes or motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iannopoulos
    -0.87
    achu
    -0.80
    umbn
    -0.79
     Flavoring
    -0.78
    oho
    -0.77
    itu
    -0.76
    assium
    -0.74
    iao
    -0.73
    ANN
    -0.71
    aido
    -0.71
    POSITIVE LOGITS
     driven
    1.05
    driving
    0.93
     driving
    0.93
    vable
    0.83
    driven
    0.74
     Dri
    0.74
     handc
    0.72
     drives
    0.72
    bys
    0.72
    whe
    0.68
    Act Density 0.017%

    No Known Activations