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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate action completion

    oai_token-act-pair · gpt-3.5-turbo

    the presence of sentences and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enroll
    -0.85
     credential
    -0.83
     emanc
    -0.82
     authorized
    -0.80
     privileged
    -0.80
     enrolled
    -0.79
     enrol
    -0.79
    eteen
    -0.78
     distribut
    -0.78
     invitation
    -0.77
    POSITIVE LOGITS
     Especially
    1.37
     Whilst
    1.33
     Hopefully
    1.32
     Basically
    1.32
     ;)
    1.31
     Anyway
    1.31
     :)
    1.29
     Secondly
    1.28
     Unfortunately
    1.27
     Otherwise
    1.27
    Act Density 0.907%

    No Known Activations