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

    Neuronpedia

    INDEX
    Explanations

    references to positions or roles within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asta
    -0.15
    ogany
    -0.15
    shake
    -0.15
    vertisement
    -0.15
    ackage
    -0.15
    uya
    -0.14
    ovy
    -0.14
    Nova
    -0.14
    riel
    -0.14
    leÅŁ
    -0.14
    POSITIVE LOGITS
    stance
    0.18
    point
    0.18
    yonel
    0.17
    ality
    0.17
    oles
    0.16
    hips
    0.16
    positions
    0.16
    over
    0.15
    embro
    0.15
    hower
    0.15
    Act Density 0.045%

    No Known Activations