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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.53
    RectangleBorder
    -0.53
    TagMode
    -0.52
     Distrikt
    -0.49
    dinga
    -0.48
     временем
    -0.47
     garanzia
    -0.47
    ContentValues
    -0.46
    multirow
    -0.44
    tableFuture
    -0.42
    POSITIVE LOGITS
    发表于
    0.74
    utilisons
    0.68
    Билгалдахарш
    0.67
    expandindo
    0.67
     FontFamily
    0.64
    帖最后由
    0.63
     Paglinawan
    0.58
    ORMAL
    0.57
    Traducción
    0.57
    ATUM
    0.57
    Act Density 0.247%

    No Known Activations