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

    Neuronpedia

    INDEX
    Explanations

    indicators of emotional expression or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.55
    timed
    -0.49
    ímite
    -0.49
     vícti
    -0.47
    彷
    -0.47
    studded
    -0.47
    pheres
    -0.47
    YON
    -0.46
    Genial
    -0.46
    XmlElement
    -0.46
    POSITIVE LOGITS
    ագրություններ
    0.69
    تقاوى
    0.68
    וויק
    0.66
    Билгалдахарш
    0.65
     StringTokenizer
    0.61
     beginnetje
    0.57
    HomeAsUpEnabled
    0.57
     تانيه
    0.57
    eseorang
    0.56
    expandindo
    0.56
    Act Density 0.702%

    No Known Activations