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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions and expressions of disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chie
    -0.17
    ób
    -0.16
    ãĥ³ãĤ¸
    -0.16
    ascript
    -0.15
    enie
    -0.15
    ucle
    -0.15
    htar
    -0.14
    radan
    -0.14
    elog
    -0.14
    elly
    -0.14
    POSITIVE LOGITS
     yes
    0.56
     Yes
    0.50
     YES
    0.49
    Yes
    0.45
    yes
    0.43
    YES
    0.40
     Nope
    0.35
    _YES
    0.33
    =yes
    0.33
    .Yes
    0.32
    Act Density 0.137%

    No Known Activations