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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive determiners linked to a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to identity and belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.64
    Bur
    -0.62
    Orig
    -0.59
    çīĪ
    -0.58
    utsche
    -0.58
    rule
    -0.57
    Eva
    -0.56
    giene
    -0.56
    æ©Ł
    -0.55
     scrimmage
    -0.55
    POSITIVE LOGITS
    urated
    0.84
    ioned
    0.78
    idered
    0.74
    itable
    0.72
    amed
    0.71
     wiser
    0.70
    omorphic
    0.70
    ouched
    0.69
     fruitful
    0.68
    versible
    0.68
    Act Density 0.619%

    No Known Activations