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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions related to power dynamics and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udge
    -0.15
    anean
    -0.15
    uds
    -0.15
    icus
    -0.15
    ibar
    -0.15
    ERCHANT
    -0.15
    cratch
    -0.14
    ampus
    -0.14
    391
    -0.14
    .gs
    -0.14
    POSITIVE LOGITS
    ê·ł
    0.14
    adesh
    0.14
    GenericType
    0.14
    ëĦ·
    0.14
    ValuePair
    0.14
     Äijình
    0.13
    owell
    0.13
    íĤ
    0.13
     Brush
    0.13
    ↵
    0.13
    Act Density 0.152%

    No Known Activations