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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the inability to resist or stop doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    วà¸ĩ
    -0.16
    izzle
    -0.15
    olas
    -0.15
    oya
    -0.15
    á»Ĩ
    -0.15
    atch
    -0.14
    úng
    -0.13
    æħĮ
    -0.13
    amento
    -0.13
    qing
    -0.13
    POSITIVE LOGITS
     notice
    0.22
     being
    0.21
     but
    0.20
     wonder
    0.19
     noticed
    0.19
     notices
    0.18
     Notices
    0.18
     noticing
    0.18
     feeling
    0.17
    lessly
    0.17
    Act Density 0.011%

    No Known Activations