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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and inquiries for clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    braco
    -0.16
    ÏĦί
    -0.15
     critique
    -0.14
    263
    -0.14
     vict
    -0.14
     Huck
    -0.14
    ervals
    -0.13
    ISIBLE
    -0.13
    291
    -0.13
     lac
    -0.13
    POSITIVE LOGITS
     reality
    0.19
     actual
    0.17
     realities
    0.17
     Posting
    0.16
    ddb
    0.15
     posting
    0.15
     harmless
    0.15
     situations
    0.15
    ango
    0.15
    _instances
    0.14
    Act Density 0.017%

    No Known Activations