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

    Neuronpedia

    INDEX
    Explanations

    items or references related to specific numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldown
    -0.68
    andowski
    -0.65
    ney
    -0.63
    nings
    -0.61
    ynski
    -0.60
    iary
    -0.58
    tones
    -0.57
    aunder
    -0.57
     senses
    -0.56
    ault
    -0.56
    POSITIVE LOGITS
    Spoiler
    1.04
    Quote
    0.91
    ________________
    0.90
    http
    0.89
    ↵↵
    0.78
    ãĤ§
    0.74
    ................
    0.73
     \"
    0.71
    https
    0.70
    \"
    0.67
    Act Density 0.668%

    No Known Activations