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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.78
    ItemBackground
    -0.66
     Roskov
    -0.66
     aapt
    -0.65
     tartalomajánló
    -0.63
    PointerException
    -0.62
    protoc
    -0.59
     AssemblyCulture
    -0.58
    modelBuilder
    -0.58
     zlo
    -0.58
    POSITIVE LOGITS
    IntoConstraints
    0.61
     فريبيس
    0.52
    tomation
    0.50
     också
    0.47
     také
    0.45
    halten
    0.45
     lulus
    0.44
     fous
    0.44
    shafen
    0.43
    }{*}{}
    0.43
    Act Density 0.601%

    No Known Activations