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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    the name "Amanda" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istry
    -0.71
    direction
    -0.70
    grading
    -0.68
    lag
    -0.68
     presidents
    -0.66
    graded
    -0.65
    book
    -0.65
    worldly
    -0.64
    ryu
    -0.64
    eled
    -0.63
    POSITIVE LOGITS
     Amanda
    1.20
    gdala
    0.95
     Berry
    0.87
     Patricia
    0.86
     Matthews
    0.85
     Courtney
    0.84
     Tess
    0.84
     Knox
    0.84
     Nunes
    0.83
     Nicole
    0.83
    Act Density 0.006%

    No Known Activations