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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and types of dashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duled
    -0.78
    namese
    -0.74
     Angelina
    -0.74
    horabuena
    -0.74
     Chriftian
    -0.72
    substack
    -0.72
    iterranean
    -0.71
    ſs
    -0.69
     Majefty
    -0.69
     Reſ
    -0.68
    POSITIVE LOGITS
    enderror
    0.88
    ScopeManager
    0.82
    Gön
    0.78
    ，
    0.71
    Kjelder
    0.70
    verwijspagina
    0.68
     disambiguazione
    0.67
    GeneratedValue
    0.66
     but
    0.66
    parsedMessage
    0.65
    Act Density 0.059%

    No Known Activations