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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "al" and its variations, indicating a focus on certain patterns or suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.89
    soDeliveryDate
    -0.84
    ecause
    -0.83
     Committees
    -0.74
    artments
    -0.69
    enegger
    -0.69
     UID
    -0.68
    akeru
    -0.67
    ascript
    -0.64
    selves
    -0.64
    POSITIVE LOGITS
    °
    0.73
    Ŀ
    0.70
    Ĭ
    0.66
    Ö¼
    0.64
    prom
    0.63
    ê
    0.63
    ili
    0.63
    ®
    0.62
    iscons
    0.61
    edom
    0.60
    Act Density 0.257%

    No Known Activations