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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or totals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.67
    NOR
    -0.55
    aternal
    -0.55
    ©¶æ
    -0.54
    atson
    -0.54
    atten
    -0.51
    STR
    -0.50
    rums
    -0.50
    Planet
    -0.49
    ENTS
    -0.49
    POSITIVE LOGITS
     of
    1.54
    of
    1.49
     OF
    1.28
     Of
    1.26
    Of
    1.25
     thereof
    1.13
    oft
    1.00
    OF
    1.00
    76561
    0.69
    uary
    0.68
    Act Density 0.161%

    No Known Activations