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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consideration or attention directed towards different topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the expression of perspectives or considerations on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.71
     submar
    -0.66
    egg
    -0.65
     preached
    -0.62
     tatt
    -0.60
     Straw
    -0.60
     Panc
    -0.59
     Clojure
    -0.59
     Guth
    -0.58
    mith
    -0.58
    POSITIVE LOGITS
    rection
    0.85
    ments
    0.81
    perature
    0.80
    ibility
    0.79
    rients
    0.77
    rait
    0.76
    equality
    0.76
    rity
    0.76
    orea
    0.75
    tains
    0.75
    Act Density 0.027%

    No Known Activations