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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive forms of "he" and "his."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reeNode
    -0.08
     ogs
    -0.07
    omik
    -0.07
    lasses
    -0.07
    ¶Į
    -0.07
    eln
    -0.07
    ковÑĸ
    -0.07
    евид
    -0.07
    ertainment
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
     or
    0.10
    /her
    0.08
    /she
    0.06
    onom
    0.06
    彼女
    0.06
    (.)
    0.06
     sil
    0.06
     she
    0.06
    yo
    0.06
    osph
    0.06
    Act Density 0.004%

    No Known Activations