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

    Neuronpedia

    INDEX
    Explanations

    words related to political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    words related to various academic or scholarly topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VPN
    -0.74
    ËĪ
    -0.73
    haar
    -0.72
    mire
    -0.70
    âĵĺ
    -0.69
    IRD
    -0.69
    limit
    -0.67
    IDENT
    -0.66
    robe
    -0.65
    gat
    -0.65
    POSITIVE LOGITS
    ity
    1.04
    ities
    0.94
    ical
    0.91
     Pwr
    0.90
    ization
    0.82
    ité
    0.80
    onduct
    0.79
    ism
    0.78
    ized
    0.78
    abama
    0.75
    Act Density 0.020%

    No Known Activations