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

    Neuronpedia

    INDEX
    Explanations

    words related to spoilage or being spoiled

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spoiling and warehousing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arette
    -0.82
    oresc
    -0.70
    uel
    -0.69
    arettes
    -0.67
    ivas
    -0.67
    uations
    -0.67
    iva
    -0.66
    oline
    -0.65
    iosity
    -0.65
    uate
    -0.65
    POSITIVE LOGITS
    housing
    1.14
    fare
    0.93
    flies
    0.89
    ledged
    0.89
    nown
    0.88
    SourceFile
    0.87
    nesses
    0.84
    ewater
    0.82
    sonian
    0.82
    worn
    0.81
    Act Density 0.070%

    No Known Activations