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

    Neuronpedia

    INDEX
    Explanations

    names or titles with the suffix "ji"

    oai_token-act-pair · gpt-3.5-turbo

    references to honorifics or titles associated with respect in a cultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.91
    holders
    -0.85
    erness
    -0.80
    acity
    -0.77
    ivities
    -0.74
    ishly
    -0.74
    uve
    -0.71
    chell
    -0.70
    acious
    -0.70
    iary
    -0.69
    POSITIVE LOGITS
    utsu
    0.91
    upiter
    0.82
    itsu
    0.79
    ordan
    0.78
    ealous
    0.76
    Ń·
    0.74
    lda
    0.74
    urnal
    0.72
    oji
    0.72
    ames
    0.72
    Act Density 0.038%

    No Known Activations