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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing facts or information

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain significant punctuation or structural markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contempl
    -0.86
     clut
    -0.85
     challeng
    -0.81
     heav
    -0.80
     emotion
    -0.80
     clutching
    -0.80
     pit
    -0.78
     indec
    -0.78
     clutch
    -0.78
     workspace
    -0.77
    POSITIVE LOGITS
     Indeed
    1.39
     Moreover
    1.34
     And
    1.31
     Presumably
    1.27
     Notably
    1.26
     Likewise
    1.25
     But
    1.25
     Therefore
    1.23
     Specifically
    1.22
     Interestingly
    1.22
    Act Density 0.777%

    No Known Activations