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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the presence or action of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scl
    -0.17
    oupon
    -0.16
    uto
    -0.15
     æ¥
    -0.15
    979
    -0.15
    uro
    -0.15
    und
    -0.15
    ald
    -0.14
    encent
    -0.14
    unders
    -0.14
    POSITIVE LOGITS
    addin
    0.16
    aliz
    0.15
    reeze
    0.15
    adla
    0.15
    distributed
    0.15
    æģ¯
    0.14
    BindingUtil
    0.14
    nge
    0.14
    ONGL
    0.13
    rve
    0.13
    Act Density 0.038%

    No Known Activations