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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enga
    -0.18
    ãĥ«ãĥī
    -0.15
    ond
    -0.15
    ouis
    -0.15
     Vys
    -0.14
     Haven
    -0.14
    haven
    -0.14
     Ult
    -0.14
    HandlerContext
    -0.14
    IENT
    -0.14
    POSITIVE LOGITS
    zelf
    0.22
    SELF
    0.19
    -même
    0.18
    /us
    0.17
    iyet
    0.17
     mình
    0.16
    áºŃt
    0.16
     himself
    0.15
     herself
    0.15
    adow
    0.15
    Act Density 0.112%

    No Known Activations