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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases involving direct speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of spoken dialogue or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folio
    -0.83
    abase
    -0.80
    Ranked
    -0.78
    unning
    -0.71
    mite
    -0.69
    osponsors
    -0.68
    ardless
    -0.68
    idious
    -0.67
    imates
    -0.66
     resorts
    -0.66
    POSITIVE LOGITS
     loudly
    1.21
     aloud
    1.10
     hello
    1.04
     plaint
    0.98
     Goodbye
    0.96
     goodbye
    0.96
     softly
    0.95
     angrily
    0.90
     unint
    0.90
     calmly
    0.84
    Act Density 0.233%

    No Known Activations