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

    Neuronpedia

    INDEX
    Explanations

    the word "real" or related terms referring to authenticity or concrete existence

    oai_token-act-pair · gpt-3.5-turbo

    terms that emphasize the absence or lack of something significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.82
     Beware
    -0.82
    alian
    -0.74
    sometimes
    -0.74
     beware
    -0.72
    clair
    -0.71
    gypt
    -0.71
    bane
    -0.70
     Slowly
    -0.69
    anwhile
    -0.69
    POSITIVE LOGITS
     whatsoever
    1.06
     indication
    0.97
     reason
    0.92
     explanation
    0.90
     substantive
    0.89
     numerical
    0.85
     recourse
    0.85
     reperc
    0.83
     distinction
    0.81
     nor
    0.81
    Act Density 0.163%

    No Known Activations