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

    Neuronpedia

    INDEX
    Explanations

    sentences or short phrases that end with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commissioned
    -0.82
     planned
    -0.81
     millenn
    -0.81
     intended
    -0.80
     predec
    -0.80
     concess
    -0.79
     authorized
    -0.79
     emanc
    -0.78
     differential
    -0.77
     designated
    -0.76
    POSITIVE LOGITS
     Anyway
    1.58
    Anyway
    1.53
     Especially
    1.40
     [/
    1.25
     Honestly
    1.23
     Secondly
    1.21
     Sorry
    1.20
     ;)
    1.19
     Besides
    1.16
     Seriously
    1.15
    Act Density 0.433%

    No Known Activations