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

    Neuronpedia

    INDEX
    Explanations

    concepts related to rules, regulations, or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omi
    -0.17
    æı¡
    -0.14
     Sunder
    -0.14
    nik
    -0.14
    _asm
    -0.14
    okol
    -0.14
    isser
    -0.14
    ney
    -0.14
    .defer
    -0.14
    446
    -0.14
    POSITIVE LOGITS
     Rica
    0.18
    ils
    0.16
    лÑıÑĤÑĮ
    0.15
    STYPE
    0.14
    resh
    0.14
    avs
    0.14
     Lace
    0.14
    çº
    0.14
    esta
    0.14
     Äijá»ģ
    0.14
    Act Density 0.009%

    No Known Activations