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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with accents

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical or political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chilling
    -0.68
    WARD
    -0.67
    ioned
    -0.65
     Worldwide
    -0.64
     Bott
    -0.61
    consumer
    -0.61
    ISON
    -0.60
    ORED
    -0.60
    IAL
    -0.59
     Rockefeller
    -0.59
    POSITIVE LOGITS
    È
    1.44
    ³
    1.08
    ofer
    0.93
    auld
    0.91
    Ļ
    0.91
    achu
    0.88
    Ľ
    0.87
    irit
    0.87
    zzo
    0.86
    ĺ
    0.85
    Act Density 0.006%

    No Known Activations