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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns in HTML-like content

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -1.01
     tremend
    -0.92
     fortun
    -0.80
     nodd
    -0.77
     confir
    -0.76
     paralyzed
    -0.75
     manif
    -0.75
     sophistic
    -0.74
     bounded
    -0.73
     unnecess
    -0.70
    POSITIVE LOGITS
    </
    0.86
    &
    0.85
    gt
    0.84
    display
    0.81
    amp
    0.80
    lt
    0.78
    ohm
    0.78
    Tang
    0.77
    [/
    0.76
    \">
    0.76
    Act Density 0.020%

    No Known Activations