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

    Neuronpedia

    INDEX
    Explanations

    instances of passive voice construction or mentions of admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apg
    -0.17
    REAM
    -0.16
    incinn
    -0.16
    orman
    -0.16
    reat
    -0.14
    reater
    -0.14
    ohon
    -0.14
    odom
    -0.14
    iane
    -0.14
    amarin
    -0.14
    POSITIVE LOGITS
    kaz
    0.16
    kö
    0.15
    нка
    0.14
    ers
    0.14
     Blank
    0.14
     bio
    0.14
    laden
    0.14
    uku
    0.14
    iar
    0.14
    iy
    0.13
    Act Density 0.051%

    No Known Activations