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

    Neuronpedia

    INDEX
    Explanations

    words related to rippling effects or repetitive patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numer
    -0.16
    rame
    -0.16
    unn
    -0.15
    æĹıèĩªæ²»
    -0.15
    åѦä¼ļ
    -0.15
    ess
    -0.15
    vap
    -0.14
    ecure
    -0.14
    ivery
    -0.14
     tort
    -0.14
    POSITIVE LOGITS
    anning
    0.16
    cord
    0.15
    jÅ¡ÃŃ
    0.15
    crc
    0.14
    ãĥ¼ãĥŃ
    0.14
    ิà¸ĩ
    0.14
    jn
    0.14
    xcf
    0.14
    ัà¸ģษ
    0.14
    sticks
    0.13
    Act Density 0.006%

    No Known Activations