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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences emphasizing the need, redundancy, or obviousness of a statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a concession or conditional statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.71
    nell
    -0.68
    lain
    -0.68
    ortium
    -0.66
    terday
    -0.65
    neys
    -0.62
    backs
    -0.61
    NING
    -0.60
    Rated
    -0.57
    utm
    -0.57
    POSITIVE LOGITS
     say
    0.97
    Say
    0.72
     SAY
    0.71
     conclude
    0.68
    lege
    0.65
     mention
    0.64
     reiterate
    0.64
     emphas
    0.63
     underscore
    0.63
     exaggeration
    0.62
    Act Density 0.055%

    No Known Activations