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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning or pondering

    oai_token-act-pair · gpt-3.5-turbo

    expressions of curiosity or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orest
    -0.58
    ortunately
    -0.57
    gradation
    -0.57
     practition
    -0.54
    ĪĴ
    -0.54
     Destruction
    -0.53
    ãĥł
    -0.52
    ikuman
    -0.52
    Torrent
    -0.51
    ãĥĨ
    -0.51
    POSITIVE LOGITS
     aloud
    1.59
     why
    1.43
     whether
    1.38
     if
    1.29
     WHY
    1.24
    why
    1.20
     how
    1.19
    whether
    1.15
     what
    1.10
     whence
    1.06
    Act Density 0.047%

    No Known Activations