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

    Neuronpedia

    INDEX
    Explanations

    references to personal responsibility and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cky
    -0.17
    andra
    -0.16
    otch
    -0.15
    CEE
    -0.15
    تÙħ
    -0.14
    affen
    -0.14
    pell
    -0.14
    avis
    -0.14
    åij½
    -0.14
    lfw
    -0.13
    POSITIVE LOGITS
    ALSE
    0.16
    hazi
    0.15
     Insets
    0.15
    oward
    0.14
    ATUS
    0.14
     Aeros
    0.14
    .scalablytyped
    0.14
    нимаÑĤÑĮ
    0.13
    ipi
    0.13
     seating
    0.13
    Act Density 0.419%

    No Known Activations