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

    Neuronpedia

    INDEX
    Explanations

    words related to hierarchical status or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogany
    -0.17
    ackage
    -0.16
    Nova
    -0.16
    asta
    -0.15
    vertisement
    -0.14
    bage
    -0.14
    shake
    -0.14
    leÅŁ
    -0.14
    oftware
    -0.14
    endale
    -0.14
    POSITIVE LOGITS
    point
    0.17
    stance
    0.17
    yonel
    0.17
    ality
    0.17
    positions
    0.16
    embro
    0.15
    hips
    0.15
    oles
    0.15
    =pos
    0.15
    OLE
    0.14
    Act Density 0.052%

    No Known Activations