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

    Neuronpedia

    INDEX
    Explanations

    content related to spam, illegal activities, and abusive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onn
    -0.16
    аем
    -0.16
    Ops
    -0.14
    uro
    -0.14
     Herr
    -0.14
    Sil
    -0.14
    okes
    -0.14
     Jab
    -0.14
     Dunn
    -0.13
    ugg
    -0.13
    POSITIVE LOGITS
    âm
    0.18
     pulp
    0.17
     pul
    0.17
     anybody
    0.16
    fusion
    0.15
    assin
    0.15
     Barrier
    0.15
    UED
    0.15
     Pul
    0.14
     anyone
    0.14
    Act Density 0.352%

    No Known Activations