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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or entities involved in activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.69
    ths
    -0.62
    utations
    -0.60
    ince
    -0.60
    cel
    -0.60
    sth
    -0.59
    any
    -0.59
    fml
    -0.58
    dn
    -0.58
    ises
    -0.57
    POSITIVE LOGITS
    whose
    0.95
     whose
    0.92
     which
    0.86
     aka
    0.85
     namely
    0.83
    which
    0.81
     meanwhile
    0.73
     who
    0.70
    who
    0.70
     formerly
    0.69
    Act Density 0.654%

    No Known Activations