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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, potentially focusing on political figures, events, and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.96
     GEAR
    -0.76
    igslist
    -0.73
    aeda
    -0.71
    anwhile
    -0.70
    umar
    -0.68
    anova
    -0.66
    UTE
    -0.65
     Yugoslav
    -0.65
     mileage
    -0.64
    POSITIVE LOGITS
    ewater
    1.29
    bread
    1.17
    eness
    1.10
    eless
    1.07
    ened
    1.03
    ening
    1.02
    elist
    0.99
    estone
    0.97
    robe
    0.95
    ecast
    0.94
    Act Density 0.089%

    No Known Activations