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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate numerical values or ranges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pert
    -0.16
     Du
    -0.15
     middle
    -0.15
     post
    -0.14
     Maj
    -0.14
    aiser
    -0.14
    iva
    -0.14
     Sed
    -0.14
     m
    -0.14
    [++
    -0.14
    POSITIVE LOGITS
    499
    0.20
    99
    0.18
    999
    0.18
    359
    0.17
     dziew
    0.17
    [--
    0.16
    ihan
    0.16
    abela
    0.16
    SCALL
    0.16
    angelog
    0.15
    Act Density 0.160%

    No Known Activations