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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of personal thoughts or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĩи
    -0.17
    uki
    -0.15
    umba
    -0.14
    mong
    -0.14
    oco
    -0.14
    oken
    -0.14
    éĬĢ
    -0.13
     Hud
    -0.13
    legates
    -0.13
     Toni
    -0.13
    POSITIVE LOGITS
    /REC
    0.16
    -clock
    0.16
    èm
    0.15
    akat
    0.14
    à¹ģà¸Ļ
    0.14
     Wells
    0.14
     wel
    0.14
    Cha
    0.13
    bens
    0.13
    iez
    0.13
    Act Density 0.187%

    No Known Activations