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

    Neuronpedia

    INDEX
    Explanations

    words related to perspectives or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to perspectives or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ternity
    -0.60
    essen
    -0.58
    arser
    -0.54
    asper
    -0.52
    ansson
    -0.49
    quer
    -0.48
    WOR
    -0.48
     Eug
    -0.48
    iguous
    -0.48
    zan
    -0.47
    POSITIVE LOGITS
     of
    1.45
    Of
    1.29
    of
    1.21
     Of
    1.16
     thereof
    1.11
     OF
    1.10
    OF
    0.88
    oft
    0.82
    luster
    0.73
    atical
    0.71
    Act Density 0.566%

    No Known Activations