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

    Neuronpedia

    INDEX
    Explanations

    prominent or well-known individuals and names within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or influential figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.77
    rontal
    -0.76
    angan
    -0.73
    oked
    -0.69
    bian
    -0.68
    awar
    -0.66
    ebin
    -0.66
    Operation
    -0.65
     Winds
    -0.65
    ı
    -0.65
    POSITIVE LOGITS
    hips
    1.09
    hip
    0.94
     alike
    0.91
    paces
    0.82
     who
    0.81
     strut
    0.79
     vying
    0.79
    acements
    0.79
     whom
    0.74
     emerge
    0.71
    Act Density 0.347%

    No Known Activations