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

    Neuronpedia

    INDEX
    Explanations

    references to identity, inclusion, and societal roles within complex narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .heroku
    -0.08
    ULSE
    -0.08
    \grid
    -0.07
    ifter
    -0.07
    REFERRED
    -0.07
    OrUpdate
    -0.07
     Bucc
    -0.07
    leme
    -0.07
    either
    -0.07
    @brief
    -0.07
    POSITIVE LOGITS
     myself
    0.12
     himself
    0.09
     themselves
    0.09
     within
    0.09
     own
    0.09
     ourselves
    0.09
     some
    0.08
     herself
    0.08
     yourself
    0.08
     even
    0.08
    Act Density 0.024%

    No Known Activations