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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    repetitive mentions of the name "Stephanie" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.96
    wagen
    -0.93
    yip
    -0.93
    intent
    -0.88
    minist
    -0.87
    etimes
    -0.86
    esty
    -0.85
    */(
    -0.83
    olesc
    -0.83
    ascript
    -0.81
    POSITIVE LOGITS
     McMahon
    1.01
     Stephanie
    0.91
     Stephens
    0.84
     Step
    0.80
    Step
    0.80
     Cutter
    0.76
     Gibbs
    0.71
     Dillon
    0.71
    Mania
    0.70
     Marie
    0.70
    Act Density 0.009%

    No Known Activations