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

    Neuronpedia

    INDEX
    Explanations

    words related to ideologies, specifically "ical" suffixes

    oai_token-act-pair · gpt-3.5-turbo

    words related to academic or systematic classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.78
    ·
    -0.77
    ËĪ
    -0.73
    VK
    -0.71
    UTF
    -0.69
    Frameworks
    -0.69
     Builder
    -0.68
     Rath
    -0.68
    HM
    -0.68
    IDA
    -0.67
    POSITIVE LOGITS
    ical
    1.10
    lihood
    0.89
    ity
    0.83
    abama
    0.82
    mares
    0.81
    upe
    0.81
    otine
    0.78
    iliated
    0.77
    urnal
    0.76
    nown
    0.75
    Act Density 0.011%

    No Known Activations