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

    Neuronpedia

    INDEX
    Explanations

    proper names related to news and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names of places, organizations, and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.70
    ©¶æ
    -0.69
     destro
    -0.68
     disposable
    -0.67
     awa
    -0.66
     thous
    -0.65
     Democr
    -0.63
     rainbow
    -0.62
     gradient
    -0.60
     abnorm
    -0.60
    POSITIVE LOGITS
    LP
    0.69
    esan
    0.68
    essor
    0.68
    )'
    0.66
    ley
    0.64
    lington
    0.62
    axter
    0.62
    endi
    0.61
    awan
    0.61
    agen
    0.61
    Act Density 0.333%

    No Known Activations