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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.73
     Eſ
    -0.72
     whoſe
    -0.69
     ſtate
    -0.69
     myſelf
    -0.67
     iſt
    -0.66
     ſeveral
    -0.66
     Diſ
    -0.65
     Conſ
    -0.65
     Reſ
    -0.64
    POSITIVE LOGITS
    
    0.63
    KommentareTeilen
    0.62
    jsxFileName
    0.60
     <<<<<<<<<<<<<<
    0.57
     easier
    0.57
    jmniej
    0.57
    脚注の使い方
    0.56
     дописавши
    0.54
     المعيارى
    0.54
    apimachinery
    0.54
    Act Density 0.190%

    No Known Activations