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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols indicative of formatting or encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bare
    -0.17
    æĿ
    -0.16
    олж
    -0.15
    nÃŃk
    -0.15
    LOOR
    -0.15
    лиÑħ
    -0.15
    ê¼
    -0.15
    еÑĤÑĮÑģÑı
    -0.15
    ãĥ³ãĤ¬
    -0.14
    à¥įरत
    -0.14
    POSITIVE LOGITS
     Port
    0.17
     surrogate
    0.16
     mur
    0.15
     Kat
    0.15
     TS
    0.14
    redential
    0.14
     port
    0.14
     Mur
    0.14
    enson
    0.14
     sur
    0.14
    Act Density 0.008%

    No Known Activations