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

    Neuronpedia

    INDEX
    Explanations

    references to branding or labeling information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪев
    -0.17
    rib
    -0.16
    .scalablytyped
    -0.16
    bern
    -0.15
    zos
    -0.14
    imli
    -0.14
     Franti
    -0.14
     Malik
    -0.14
    lament
    -0.14
    çµµ
    -0.13
    POSITIVE LOGITS
    สาร
    0.16
    é³´
    0.15
    udos
    0.15
    ATS
    0.15
    culate
    0.15
    olla
    0.15
    رسÛĮ
    0.14
    795
    0.14
     pol
    0.14
    unal
    0.13
    Act Density 0.001%

    No Known Activations