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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istics
    -0.90
    istically
    -0.84
    otle
    -0.80
    istic
    -0.76
    ouse
    -0.74
    blank
    -0.73
    ographically
    -0.72
    GM
    -0.71
    sylvania
    -0.70
    cision
    -0.69
    POSITIVE LOGITS
    apest
    0.91
     Muk
    0.89
    alla
    0.82
    ileaks
    0.82
    ulkan
    0.82
     Uz
    0.81
    utsu
    0.79
    agara
    0.78
    unda
    0.75
    htar
    0.73
    Act Density 0.027%

    No Known Activations