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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific person's name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, particularly Dr. George Tiller

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aligned
    -0.72
    estinal
    -0.71
    ðĿ
    -0.71
    rab
    -0.65
    raised
    -0.64
    change
    -0.61
    ually
    -0.60
    repeat
    -0.59
    flat
    -0.59
     Sek
    -0.59
    POSITIVE LOGITS
    iller
    1.21
    espie
    1.01
    uminati
    0.92
    apter
    0.86
    aceous
    0.83
    essen
    0.81
    azine
    0.80
    iatus
    0.79
    ionage
    0.78
    anguage
    0.77
    Act Density 0.005%

    No Known Activations