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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    00007
    -0.70
    lain
    -0.70
    wo
    -0.69
    idential
    -0.68
    0002
    -0.68
    eous
    -0.68
    aspx
    -0.67
    sburgh
    -0.67
    umber
    -0.67
     Anthem
    -0.66
    POSITIVE LOGITS
     Alison
    0.99
    ĸļ
    0.90
    aret
    0.83
    uana
    0.82
    ©¶æ¥µ
    0.80
    gebra
    0.76
     fingert
    0.73
    Ĥİ
    0.72
    ĺħ
    0.72
    irie
    0.71
    Act Density 0.014%

    No Known Activations