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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring "su" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fevere
    -0.63
     faſt
    -0.58
     ſche
    -0.57
     SafeMath
    -0.56
     ſta
    -0.55
     urllib
    -0.53
    Portail
    -0.52
    Ӕ
    -0.52
     itſelf
    -0.52
     gracilis
    -0.52
    POSITIVE LOGITS
     вы
    0.84
     wy
    0.70
     Wy
    0.66
     u
    0.59
     dumne
    0.59
    ு
    0.59
    Wy
    0.59
     Вы
    0.58
     у
    0.57
     drums
    0.56
    Act Density 0.224%

    No Known Activations