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

    Neuronpedia

    INDEX
    Explanations

    quotes or direct speech within text

    oai_token-act-pair · gpt-3.5-turbo

    direct speech or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -1.07
    osponsors
    -0.81
    folio
    -0.78
    reviewed
    -0.78
    ossier
    -0.75
    unity
    -0.75
    atcher
    -0.72
    agos
    -0.71
    folios
    -0.71
    vre
    -0.70
    POSITIVE LOGITS
     loudly
    1.29
     aloud
    1.27
     softly
    1.16
     hello
    1.09
     plaint
    1.09
     inco
    1.07
     goodbye
    1.04
     incomprehensible
    1.03
     loud
    1.03
     unint
    1.01
    Act Density 0.312%

    No Known Activations