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

    Neuronpedia

    INDEX
    Explanations

    references to discussions or explanations about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ois
    -0.16
     Stranger
    -0.15
    arendra
    -0.15
     Mari
    -0.14
     sho
    -0.14
    lero
    -0.14
    ega
    -0.14
    å¼ı
    -0.13
     æ©
    -0.13
    adj
    -0.13
    POSITIVE LOGITS
     Fal
    0.18
     practitioners
    0.18
    SSIP
    0.18
     Epoch
    0.18
    Fal
    0.16
     practitioner
    0.16
     Essen
    0.15
     Essence
    0.15
    urement
    0.15
     ìĹĨìĸ´
    0.14
    Act Density 0.002%

    No Known Activations