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

    Neuronpedia

    INDEX
    Explanations

    terms indicating mildness or low severity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.73
     utafitiHapana
    -0.71
     فريبيس
    -0.70
    BeginInit
    -0.69
     sockaddr
    -0.66
    RenderAtEndOf
    -0.65
     виправивши
    -0.65
    :][
    -0.64
    aarrggbb
    -0.63
    перь
    -0.62
    POSITIVE LOGITS
     mild
    1.75
    mild
    1.55
     lightly
    1.49
     Mild
    1.43
     lightweight
    1.42
     modest
    1.35
     légère
    1.34
    Mild
    1.32
     faint
    1.31
     gentle
    1.30
    Act Density 0.100%

    No Known Activations