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

    Neuronpedia

    INDEX
    Explanations

    words related to names or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "ark"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æµ
    -0.66
    âĸ¬âĸ¬
    -0.60
     unnecess
    -0.60
    FA
    -0.58
     Romeo
    -0.57
    IME
    -0.57
    hetically
    -0.56
    oret
    -0.56
    ISTER
    -0.56
     reckoned
    -0.56
    POSITIVE LOGITS
    ozy
    1.31
    ansas
    1.27
    entin
    1.06
    eting
    1.00
    anian
    0.96
    inson
    0.93
    itect
    0.92
    iller
    0.89
    ulic
    0.89
    enment
    0.87
    Act Density 0.042%

    No Known Activations