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

    Neuronpedia

    INDEX
    Explanations

    repeated punctuation marks and certain special formatting within code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Izvori
    -0.65
    expandindo
    -0.65
    featureID
    -0.64
    ArgsConstructor
    -0.62
    schild
    -0.60
    marshaller
    -0.59
    Controllo
    -0.58
    XmlAccessorType
    -0.58
     betweenstory
    -0.58
    openConnection
    -0.57
    POSITIVE LOGITS
    :✨
    0.90
     kasarigan
    0.82
    rungsseite
    0.82
    mtable
    0.74
     Olu
    0.70
    hdashline
    0.69
    　・
    0.69
    vaient
    0.68
     Meh
    0.68
     Paar
    0.68
    Act Density 0.003%

    No Known Activations