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

    Neuronpedia

    INDEX
    Explanations

    references to time durations or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndham
    -0.60
     فريبيس
    -0.57
     CURLOPT
    -0.55
     Normdatei
    -0.53
    dą
    -0.52
    ailles
    -0.52
     saites
    -0.49
     Jahrhunder
    -0.49
    pinephrine
    -0.48
    SBATCH
    -0.48
    POSITIVE LOGITS
     tops
    1.17
     max
    1.15
     maximum
    1.06
    give
    1.03
     minimum
    1.03
    ish
    0.97
     ish
    0.96
     MAX
    0.91
    max
    0.91
    minimum
    0.91
    Act Density 0.318%

    No Known Activations