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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to scientific concepts or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪÙĨÙĩ
    -0.16
    ppard
    -0.16
    ives
    -0.15
    ived
    -0.15
    imbus
    -0.14
    aina
    -0.14
    iminal
    -0.14
    κÏħ
    -0.14
    loys
    -0.14
     guise
    -0.14
    POSITIVE LOGITS
    nut
    0.19
    osate
    0.17
    away
    0.16
    adget
    0.16
    906
    0.15
    irth
    0.15
    ëģĶ
    0.15
    busters
    0.15
    reich
    0.15
    ison
    0.14
    Act Density 0.308%

    No Known Activations