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

    Neuronpedia

    INDEX
    Explanations

    numeric values or identifiers and their various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORETICAL
    -0.56
     Monfieur
    -0.56
     ModelExpression
    -0.55
    yntaxException
    -0.53
     locker
    -0.50
     NDEBUG
    -0.50
     betweenstory
    -0.50
    Rhestr
    -0.49
    __).
    -0.49
    InitVars
    -0.49
    POSITIVE LOGITS
    rxjs
    0.67
     Himo
    0.66
    Datuak
    0.63
    userdetails
    0.56
     <=",
    0.55
    Gambas
    0.54
     ComVisible
    0.54
    Tembelea
    0.53
    ftagPool
    0.51
    0.51
    Act Density 0.175%

    No Known Activations