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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations or incidents involving them

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.86
    ratulations
    -0.83
    faced
    -0.81
    hai
    -0.70
    mun
    -0.70
     succeeded
    -0.69
    tailed
    -0.69
    rils
    -0.68
    busters
    -0.68
    Mask
    -0.65
    POSITIVE LOGITS
     afar
    1.73
     whence
    1.30
     scratch
    1.18
     abroad
    1.08
     thence
    1.00
     inside
    0.96
     inception
    0.94
     infancy
    0.87
     obscurity
    0.87
     within
    0.87
    Act Density 2.147%

    No Known Activations