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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    夫
    -0.15
    ierz
    -0.15
     Cunning
    -0.15
    ÑĢеж
    -0.15
    olute
    -0.15
    Ñģион
    -0.15
    èĥİ
    -0.14
    ении
    -0.14
    ewise
    -0.14
    upakan
    -0.14
    POSITIVE LOGITS
    rou
    0.16
    425
    0.15
     pov
    0.13
     Need
    0.13
    rod
    0.13
     AAA
    0.13
    SYS
    0.13
    /Gate
    0.13
    Atlas
    0.13
     Mis
    0.13
    Act Density 0.031%

    No Known Activations