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

    Neuronpedia

    INDEX
    Explanations

    statements that express rejection or negation of certain ideas or plans

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    igu
    -0.50
     between
    -0.50
     koy
    -0.48
     spell
    -0.48
    약
    -0.48
    ########.
    -0.47
     basically
    -0.46
     esternos
    -0.46
    counters
    -0.45
    secutions
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.94
    __))
    0.69
     disambiguazione
    0.69
    ScopeManager
    0.68
     فريبيس
    0.65
    INSEE
    0.65
     Савезне
    0.65
    olesale
    0.63
    TagMode
    0.63
    "}}
    0.62
    Act Density 0.054%

    No Known Activations