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

    Neuronpedia

    INDEX
    Explanations

    statements reflecting the frequency or prevalence of certain phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.97
    /***/
    -0.93
     nahilalakip
    -0.90
    solete
    -0.89
    ggable
    -0.89
    Портал
    -0.88
     Argus
    -0.86
    mitives
    -0.86
    gerald
    -0.84
    érience
    -0.82
    POSITIVE LOGITS
     nations
    0.94
     fibers
    0.85
     nation
    0.82
    Folks
    0.80
    a
    0.78
     Gentry
    0.77
     cilantro
    0.77
    йдет
    0.75
     NATION
    0.74
     anemia
    0.73
    Act Density 0.126%

    No Known Activations