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

    Neuronpedia

    INDEX
    Explanations

    questions expressing surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.77
    ();)
    -0.69
    awtextra
    -0.63
    AnchorStyles
    -0.62
    الحياه
    -0.61
    ("]");
    -0.61
    AutoScaleMode
    -0.61
    XmlAccessorType
    -0.60
    yorsunuz
    -0.60
    bootstrapcdn
    -0.60
    POSITIVE LOGITS
     happened
    0.89
     possessed
    0.67
    happened
    0.65
    cha
    0.63
     sorcery
    0.61
     Happened
    0.61
     HAPPENED
    0.59
     else
    0.54
     happ
    0.54
     happen
    0.54
    Act Density 0.197%

    No Known Activations