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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terms and technical jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XtraReports
    -0.43
    FXMLLoader
    -0.40
    ﹠
    -0.35
    AndroidJUnit
    -0.34
     dim
    -0.34
    cdonald
    -0.33
     règles
    -0.31
     regimes
    -0.31
     getStart
    -0.31
    ModelAdmin
    -0.30
    POSITIVE LOGITS
    수
    0.77
     수
    0.71
    Datuak
    0.68
    Razor
    0.64
    ArgsConstructor
    0.61
    lessness
    0.61
     effortless
    0.61
    less
    0.61
    数
    0.59
     Razor
    0.58
    Act Density 0.994%

    No Known Activations