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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or evaluations about various topics

    oai_token-act-pair · gpt-3.5-turbo

    opinions and subjective statements expressed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allegedly
    -0.68
    hor
    -0.66
     Written
    -0.64
    ÄŁ
    -0.63
     supposed
    -0.60
     supposedly
    -0.59
     sham
    -0.58
    rawdownloadcloneembedreportprint
    -0.58
    WB
    -0.58
    !/
    -0.58
    POSITIVE LOGITS
    pole
    0.71
    uce
    0.67
    arden
    0.67
    geist
    0.65
    cott
    0.64
     Rampage
    0.64
    Edward
    0.63
     congr
    0.63
    xus
    0.63
     goodbye
    0.62
    Act Density 0.053%

    No Known Activations