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

    Neuronpedia

    INDEX
    Explanations

    data related to formal reports and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bumper
    -0.17
    base
    -0.16
    /Sub
    -0.15
    ams
    -0.14
     Courage
    -0.14
    ġ
    -0.14
    igham
    -0.14
    over
    -0.14
    anon
    -0.13
     nond
    -0.13
    POSITIVE LOGITS
    /goto
    0.18
    usan
    0.15
    apus
    0.14
    Ļ¨
    0.14
     Král
    0.14
    kı
    0.14
    ãĥ¼ãĥĦ
    0.14
     Picker
    0.14
    ALSE
    0.13
    AreaView
    0.13
    Act Density 0.007%

    No Known Activations