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

    Neuronpedia

    INDEX
    Explanations

    names of famous individuals and specific locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.84
    cial
    -0.74
    LY
    -0.73
     Gork
    -0.72
    âĹ¼
    -0.70
    rely
    -0.69
    cffffcc
    -0.68
    bered
    -0.67
    ienced
    -0.65
    cles
    -0.65
    POSITIVE LOGITS
    iard
    1.23
    iday
    1.06
    igan
    1.05
    ows
    1.03
    igans
    0.99
    anova
    0.96
    iflower
    0.95
    wagen
    0.94
    aday
    0.92
    iston
    0.91
    Act Density 6.265%

    No Known Activations