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

    Neuronpedia

    INDEX
    Explanations

    words related to voting or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cast" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.84
     Hamp
    -0.75
    psey
    -0.73
    ĸļ
    -0.67
    £ı
    -0.67
     proble
    -0.66
     Wem
    -0.65
     Wass
    -0.65
    ¥µ
    -0.62
    pend
    -0.61
    POSITIVE LOGITS
    aways
    1.13
    igating
    0.94
     casts
    0.92
    wright
    0.92
    rated
    0.89
    ration
    0.88
    rating
    0.88
    aine
    0.87
    otom
    0.87
    lest
    0.86
    Act Density 0.014%

    No Known Activations