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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to automated actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "automatically" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.01
    ippi
    -0.84
    andals
    -0.78
    rug
    -0.75
    Liter
    -0.73
    ergus
    -0.72
    borough
    -0.70
    raints
    -0.70
    rast
    -0.69
    ,,,,
    -0.68
    POSITIVE LOGITS
     upd
    0.87
     induct
    0.87
     detect
    0.85
     populate
    0.84
    immune
    0.83
     migrate
    0.83
     grav
    0.81
     regenerate
    0.81
    isable
    0.80
     deducted
    0.80
    Act Density 0.027%

    No Known Activations