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

    Neuronpedia

    INDEX
    Explanations

    references to authors and publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondo
    -0.17
     Heard
    -0.17
    itere
    -0.15
    ãĥŃãĥ¼
    -0.14
    ÙĦÙģ
    -0.14
     cuffs
    -0.14
    acent
    -0.14
     Kou
    -0.14
    vell
    -0.14
    hin
    -0.14
    POSITIVE LOGITS
    aeda
    0.17
    Margins
    0.16
    aney
    0.15
    μμ
    0.14
    obao
    0.14
    мÑı
    0.14
    dt
    0.14
    ustos
    0.13
    'gc
    0.13
    pled
    0.13
    Act Density 0.025%

    No Known Activations