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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is able to accomplish a task

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "able" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parents
    -0.70
     Sins
    -0.68
     Caval
    -0.66
     Tradition
    -0.64
     Alone
    -0.63
     Crowley
    -0.61
     Generation
    -0.59
     Origin
    -0.59
     Bots
    -0.59
     Rising
    -0.59
    POSITIVE LOGITS
    ioned
    0.99
    reys
    0.89
    bodied
    0.88
    't
    0.86
    awaru
    0.77
    ords
    0.77
     successfully
    0.76
    istically
    0.76
    uate
    0.75
    nels
    0.74
    Act Density 0.034%

    No Known Activations