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

    Neuronpedia

    INDEX
    Explanations

    words related to character classes and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.49
    OGND
    -0.44
    arraycopy
    -0.38
     فريبيس
    -0.36
    {§
    -0.35
     föres
    -0.34
     transférez
    -0.33
    enderror
    -0.33
     tục
    -0.33
    OrBuilder
    -0.33
    POSITIVE LOGITS
    ització
    0.59
    ization
    0.58
    isation
    0.56
    ção
    0.53
    ning
    0.53
    complexContent
    0.53
    parsedMessage
    0.53
    izacao
    0.52
    ÇÃO
    0.50
    zation
    0.48
    Act Density 1.084%

    No Known Activations