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

    Neuronpedia

    INDEX
    Explanations

    public opinion statistics and survey results expressed as percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or percentages related to polls or survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.75
    ammy
    -0.73
    ãĥ¯
    -0.73
    skirts
    -0.67
    Haunted
    -0.63
     Reborn
    -0.60
     stunts
    -0.60
    adr
    -0.58
     Complex
    -0.58
    itary
    -0.58
    POSITIVE LOGITS
     disapprove
    1.40
     approve
    1.25
     surveyed
    1.23
     polled
    1.22
     agree
    1.20
     believe
    1.15
     agreed
    1.11
     disagreed
    1.11
     disappro
    1.10
     say
    1.09
    Act Density 0.128%

    No Known Activations