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

    Neuronpedia

    INDEX
    Explanations

    references to exclusion and compensation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONO
    -0.16
    ombres
    -0.15
    ternet
    -0.15
    idders
    -0.15
    ullan
    -0.14
    idian
    -0.14
    ître
    -0.13
     causa
    -0.13
    akis
    -0.13
     Saud
    -0.13
    POSITIVE LOGITS
    енз
    0.17
     accordingly
    0.17
    ateur
    0.16
     unless
    0.15
     automatically
    0.15
    ander
    0.15
    çľ
    0.15
    avid
    0.15
    ç¿
    0.14
    ral
    0.14
    Act Density 0.500%

    No Known Activations