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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to scientific measurements and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CodeAttribute
    -0.61
    alité
    -0.56
     kasarigan
    -0.55
    ensement
    -0.53
    FormTagHelper
    -0.53
    thodes
    -0.52
     مُعرِّف
    -0.51
    +:+
    -0.48
    تقاوى
    -0.48
    setMode
    -0.47
    POSITIVE LOGITS
     threshold
    0.67
    threshold
    0.62
     seuil
    0.57
    Threshold
    0.55
     Fio
    0.55
    ósz
    0.53
     Threshold
    0.53
     hinweg
    0.52
     thresholds
    0.51
     BENJAMIN
    0.50
    Act Density 1.120%

    No Known Activations