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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or patterns in transcribed or mixed language text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ved
    -0.15
    bedo
    -0.14
    lek
    -0.14
    æŁĵ
    -0.14
     ranks
    -0.14
    iev
    -0.14
    æ¢
    -0.14
    Å¡lo
    -0.13
    yun
    -0.13
     ting
    -0.13
    POSITIVE LOGITS
     u
    0.24
     sa
    0.22
     koje
    0.19
     koji
    0.19
     ko
    0.18
     Ñĥ
    0.18
     ко
    0.18
    ,u
    0.17
    (u
    0.17
     odak
    0.16
    Act Density 0.007%

    No Known Activations