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

    Neuronpedia

    INDEX
    Explanations

    patterns of repeated phrases or sentences often used to convey generalizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assis
    -0.17
     Upon
    -0.16
     Vak
    -0.16
    itten
    -0.15
     upon
    -0.15
    Upon
    -0.14
    iry
    -0.14
    eneg
    -0.13
    353
    -0.13
    iber
    -0.13
    POSITIVE LOGITS
    kü
    0.19
    943
    0.16
    (coder
    0.15
    оÑģÑĤ
    0.15
     ÙģÙĩ
    0.15
    æ·¡
    0.15
    üstü
    0.14
     Rim
    0.14
     ilma
    0.14
    iffies
    0.14
    Act Density 0.164%

    No Known Activations