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

    Neuronpedia

    INDEX
    Explanations

    words related to personas or individuals, specifically names like "Sophie," "Sophia," or "Sofia."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Sophie" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     FORM
    -0.71
    eed
    -0.65
    BAT
    -0.65
    âĸ¬âĸ¬
    -0.62
    hips
    -0.60
    redo
    -0.59
    forth
    -0.59
    LESS
    -0.58
    ARDS
    -0.58
    MENTS
    -0.57
    POSITIVE LOGITS
    sylv
    0.91
    osph
    0.90
    otos
    0.86
    aea
    0.84
    inx
    0.81
    ongyang
    0.79
    osure
    0.79
    sta
    0.77
    ofer
    0.77
    phony
    0.76
    Act Density 0.038%

    No Known Activations