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

    Neuronpedia

    INDEX
    Explanations

    possessive and indicative pronouns or determiners used in contexts related to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëł
    -0.16
    ÑŁ
    -0.15
    .ga
    -0.15
    suite
    -0.14
    UGH
    -0.14
    .yahoo
    -0.14
     ABOVE
    -0.14
    iones
    -0.14
    starts
    -0.14
     nejd
    -0.13
    POSITIVE LOGITS
    1
    0.36
     ï
    0.22
     fist
    0.20
     lst
    0.20
     maiden
    0.20
     fi
    0.20
     fis
    0.20
     very
    0.19
     fr
    0.19
     inaugural
    0.19
    Act Density 0.075%

    No Known Activations