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

    Neuronpedia

    INDEX
    Explanations

    themes related to personal identity and self-expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eya
    -0.15
    ÏĢε
    -0.14
     blind
    -0.14
    abase
    -0.13
    394
    -0.13
    urahan
    -0.13
     Batch
    -0.13
    onas
    -0.13
    urity
    -0.13
     Gross
    -0.13
    POSITIVE LOGITS
     selves
    0.33
     version
    0.29
    -version
    0.27
     versions
    0.27
     Version
    0.26
     Versions
    0.26
    .version
    0.26
     oneself
    0.25
    versions
    0.25
     person
    0.25
    Act Density 0.215%

    No Known Activations