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

    Neuronpedia

    INDEX
    Explanations

    numerical rankings or placements in competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appen
    -0.15
     husus
    -0.15
    лаж
    -0.15
    ÑĭÑĪ
    -0.14
    æ´
    -0.14
    chop
    -0.14
    _FOREACH
    -0.14
    STA
    -0.13
    .sg
    -0.13
    ologne
    -0.13
    POSITIVE LOGITS
     Vall
    0.16
    iyon
    0.16
    iones
    0.15
    uÄį
    0.15
     among
    0.15
    eyen
    0.14
    _VENDOR
    0.14
     fraction
    0.14
    erna
    0.14
    .dk
    0.14
    Act Density 0.004%

    No Known Activations