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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges or limits

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating maximum limits or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    birds
    -0.66
    brook
    -0.66
    Moving
    -0.64
    rats
    -0.64
    went
    -0.64
     Wiz
    -0.63
    NEY
    -0.62
     Perspective
    -0.59
    Reviewer
    -0.59
    Smart
    -0.58
    POSITIVE LOGITS
    pload
    1.04
    capacity
    0.79
    perty
    0.75
     date
    0.74
    200000
    0.73
    kw
    0.71
    thirds
    0.71
    atever
    0.70
    abyte
    0.70
    undreds
    0.65
    Act Density 0.039%

    No Known Activations