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

    Neuronpedia

    INDEX
    Explanations

    phrases involving making choices between different options

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to choices or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.85
    OGR
    -0.83
    tsy
    -0.78
    wikipedia
    -0.78
    gow
    -0.77
    rak
    -0.76
    brate
    -0.74
    riz
    -0.74
    der
    -0.72
    oÄŁ
    -0.71
    POSITIVE LOGITS
     halves
    0.85
     genders
    0.75
     them
    0.72
     competing
    0.70
     two
    0.67
     sexes
    0.67
     extremes
    0.66
     scarce
    0.66
     genres
    0.62
     Anarchy
    0.62
    Act Density 0.038%

    No Known Activations