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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     immersion
    -0.76
     cannibal
    -0.74
     manif
    -0.73
     solution
    -0.71
     bonding
    -0.71
     charm
    -0.71
     purse
    -0.71
     drill
    -0.70
     misunderstood
    -0.70
     commuting
    -0.70
    POSITIVE LOGITS
    NET
    1.16
    jpg
    0.99
    taboola
    0.99
     âĶľâĶĢâĶĢ
    0.97
    embed
    0.92
    pdf
    0.91
    gif
    0.90
    \-
    0.89
    html
    0.89
    htm
    0.89
    Act Density 0.049%

    No Known Activations