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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks commonly used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zijne
    -0.46
     étoit
    -0.45
     desnuda
    -0.45
     Rücksicht
    -0.43
     esclavos
    -0.42
     fisuras
    -0.42
     overras
    -0.41
     femenina
    -0.40
     cementerio
    -0.40
     vuestros
    -0.40
    POSITIVE LOGITS
     ब्रेकडाउन
    0.82
     autorytatywna
    0.82
    AutoScaleMode
    0.81
    ,
    0.79
    utilisons
    0.79
     consultato
    0.79
     CanadaChoose
    0.77
    PyExc
    0.74
    SequentialGroup
    0.73
     ffilmiau
    0.73
    Act Density 0.962%

    No Known Activations