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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inson
    -0.17
    umbing
    -0.16
    utt
    -0.15
     Å
    -0.15
    usters
    -0.14
     průbÄĽhu
    -0.14
    aternity
    -0.13
    ysis
    -0.13
    utor
    -0.13
     Trevor
    -0.13
    POSITIVE LOGITS
    OffsetTable
    0.16
    اÙĩ
    0.15
     similarly
    0.15
    Ïģιά
    0.15
    teg
    0.15
    dice
    0.14
    isko
    0.14
    robat
    0.14
    dex
    0.14
     similar
    0.14
    Act Density 0.106%

    No Known Activations