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

    Neuronpedia

    INDEX
    Explanations

    words related to exceeding or surpassing certain limits or numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surpassing or exceeding limits or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atto
    -0.72
    letter
    -0.68
    BUG
    -0.67
    rug
    -0.62
    seed
    -0.61
    otta
    -0.61
    rain
    -0.60
    ale
    -0.59
     breeze
    -0.59
    uzzle
    -0.58
    POSITIVE LOGITS
     expectations
    1.11
    İĭ
    0.77
    assis
    0.77
    hap
    0.75
     milestones
    0.72
     400
    0.68
     thresholds
    0.67
    atos
    0.67
     orgasm
    0.66
    Ń·
    0.66
    Act Density 0.063%

    No Known Activations