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

    Neuronpedia

    INDEX
    Explanations

    words related to software or code implementation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of software or technical implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onna
    -0.80
    ighth
    -0.68
    imir
    -0.68
    ovies
    -0.67
    azines
    -0.67
     Flavoring
    -0.65
     lodge
    -0.65
     Gaia
    -0.65
    cery
    -0.63
     Inquisitor
    -0.62
    POSITIVE LOGITS
    urally
    1.03
    plementation
    0.91
     implementations
    0.90
    emonium
    0.80
    ural
    0.80
    SourceFile
    0.75
    ãĤ´
    0.74
     implemented
    0.72
     implementation
    0.72
    atable
    0.71
    Act Density 0.017%

    No Known Activations