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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific place names or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.76
    ELS
    -0.73
    ItemTracker
    -0.72
    ALLY
    -0.72
    FG
    -0.68
    IRD
    -0.68
    olicy
    -0.66
    ERN
    -0.66
    SourceFile
    -0.65
    EEE
    -0.64
    POSITIVE LOGITS
    beck
    1.00
    inker
    1.00
    enium
    0.95
    ved
    0.95
    anguage
    0.94
    seys
    0.92
    zer
    0.92
    mer
    0.91
    ena
    0.90
    vag
    0.90
    Act Density 0.007%

    No Known Activations