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

    Neuronpedia

    INDEX
    Explanations

    a specific word, "faisal," possibly related to a person's name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ais"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.79
    ographers
    -0.78
    OGR
    -0.74
    ICES
    -0.73
    dfx
    -0.71
     externalToEVAOnly
    -0.71
    ographically
    -0.70
    oter
    -0.68
    kernel
    -0.68
    ohyd
    -0.67
    POSITIVE LOGITS
    hip
    0.95
    ateur
    0.89
    auga
    0.89
    eme
    0.87
    olate
    0.85
    ais
    0.83
    chwitz
    0.82
    ai
    0.78
    aurus
    0.77
    -|
    0.77
    Act Density 0.020%

    No Known Activations