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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "I" indicating personal narratives or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bian
    -0.18
    ilion
    -0.16
    bis
    -0.15
    alars
    -0.15
    inals
    -0.14
     stret
    -0.14
    ScreenState
    -0.14
     Inquiry
    -0.14
    izo
    -0.14
    ican
    -0.14
    POSITIVE LOGITS
    eless
    0.15
     Sexe
    0.15
    ibri
    0.15
    ivated
    0.14
    ethyst
    0.14
     Rouge
    0.14
    ạp
    0.14
    otty
    0.14
    cul
    0.14
    srv
    0.14
    Act Density 0.056%

    No Known Activations