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

    Neuronpedia

    INDEX
    Explanations

    statistical averages and measures of central tendency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DialogInterface
    -0.72
     Musk
    -0.63
    ̀n
    -0.60
     emb
    -0.60
    hasMoreElements
    -0.58
    servez
    -0.58
     Thorne
    -0.57
    ˈ
    -0.57
     zak
    -0.55
    볍
    -0.55
    POSITIVE LOGITS
     AVERAGE
    1.48
     averages
    1.42
     Average
    1.41
     averaging
    1.41
     averaged
    1.38
    average
    1.38
    verages
    1.37
    Average
    1.37
     Avg
    1.36
    AVERAGE
    1.36
    Act Density 0.108%

    No Known Activations