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

    Neuronpedia

    INDEX
    Explanations

    the word "rit" with varying activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Pritchard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶ħ
    -0.85
    ĨĴ
    -0.82
    ©¶æ
    -0.75
    ĻĤ
    -0.75
    «ĺ
    -0.74
    ŃĶ
    -0.71
     instantaneous
    -0.68
    é¾
    -0.67
    ¥ŀ
    -0.65
    Merit
    -0.62
    POSITIVE LOGITS
    rit
    1.10
    ual
    1.04
    chard
    0.90
    ravel
    0.89
    krit
    0.89
    igi
    0.83
    ually
    0.82
    ika
    0.81
    sis
    0.81
    ions
    0.80
    Act Density 0.007%

    No Known Activations