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

    Neuronpedia

    INDEX
    Explanations

    references to clips or segments in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.77
    GEBURTSDATUM
    -0.73
    ValueStyle
    -0.71
    tsin
    -0.69
     preſ
    -0.67
     myſelf
    -0.66
     whoſe
    -0.64
    SharedCtor
    -0.63
     faſt
    -0.62
     Efq
    -0.61
    POSITIVE LOGITS
     clip
    0.90
     Clip
    0.83
     cave
    0.79
    Clip
    0.77
     Cave
    0.75
    ane
    0.74
    stat
    0.70
    clip
    0.69
    Cave
    0.67
     clipping
    0.67
    Act Density 0.053%

    No Known Activations