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

    Neuronpedia

    INDEX
    Explanations

    specific names of individuals, particularly in the context of Japanese names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.93
     purpoſe
    -0.91
    ſelf
    -0.82
     houſe
    -0.78
     ſtand
    -0.76
     reaſon
    -0.76
    ſelves
    -0.76
     myſelf
    -0.75
     uſe
    -0.73
     pleaſure
    -0.72
    POSITIVE LOGITS
     Mr
    0.61
    Mr
    0.52
    гій
    0.52
     señor
    0.50
     senhor
    0.49
     ringan
    0.48
     sir
    0.47
     récents
    0.47
     Dr
    0.46
     cappello
    0.46
    Act Density 0.093%

    No Known Activations