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

    Neuronpedia

    INDEX
    Explanations

    terms indicating specific conditions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "certain" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inson
    -0.72
     Cum
    -0.69
    perse
    -0.68
    adia
    -0.67
    TeX
    -0.67
    INT
    -0.65
    END
    -0.63
    let
    -0.63
    DragonMagazine
    -0.63
    jet
    -0.63
    POSITIVE LOGITS
    ties
    1.40
     kinds
    1.07
     wavelengths
    0.89
    iating
    0.88
    iated
    0.87
     types
    0.83
     amount
    0.83
     thresholds
    0.80
     amounts
    0.78
     certain
    0.78
    Act Density 0.021%

    No Known Activations