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

    Neuronpedia

    INDEX
    Explanations

    medical terms or phrases related to medical procedures

    oai_token-act-pair · gpt-3.5-turbo

    bracketed text or references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imore
    -0.76
    nesday
    -0.75
    wagen
    -0.74
    ores
    -0.74
     upl
    -0.71
     imb
    -0.70
     comprom
    -0.68
     clad
    -0.68
     redu
    -0.68
     synthetic
    -0.67
    POSITIVE LOGITS
    ?]
    1.26
    !]
    1.18
    Laughs
    1.16
    Pg
    1.07
    âĢ¦]
    1.06
    Footnote
    1.06
    laughs
    1.04
    ](
    1.04
    ...]
    1.03
    emphasis
    1.02
    Act Density 0.025%

    No Known Activations