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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing skepticism or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "cast" and its variations in relation to voting or decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.75
     proble
    -0.68
    £ı
    -0.68
    COMPLE
    -0.64
    ĸļ
    -0.64
     Hamp
    -0.62
     Situation
    -0.60
    ĨĴ
    -0.60
     Wass
    -0.58
     Fres
    -0.57
    POSITIVE LOGITS
    igating
    1.08
    aways
    1.04
    igated
    1.02
    rated
    0.96
    rating
    0.96
    ration
    0.94
    aine
    0.91
     casts
    0.90
    rations
    0.88
    wright
    0.86
    Act Density 0.018%

    No Known Activations