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

    Neuronpedia

    INDEX
    Explanations

    legal terms and concepts related to liability and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     åŀ
    -0.15
    edException
    -0.15
     Exceptions
    -0.15
    Ñĸб
    -0.14
     Ib
    -0.14
    Ìĥ
    -0.14
    паÑĤ
    -0.13
     pat
    -0.13
    elt
    -0.13
    583
    -0.13
    POSITIVE LOGITS
    rani
    0.18
    uzzer
    0.15
    uur
    0.15
    ék
    0.15
    ÙģاÙĦ
    0.15
    Accessor
    0.14
    zdy
    0.14
     Carpenter
    0.14
    apel
    0.14
    ucz
    0.14
    Act Density 0.004%

    No Known Activations