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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the seriousness or importance of various subjects or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emey
    -0.16
    enheim
    -0.15
    nds
    -0.15
    abby
    -0.15
    indsight
    -0.14
    reib
    -0.14
    //{{
    -0.14
    eya
    -0.14
    ewriter
    -0.14
    éłĨ
    -0.14
    POSITIVE LOGITS
     serious
    1.22
     Serious
    1.09
    serious
    1.03
     seriousness
    1.02
     seriously
    0.98
    -ser
    0.82
     seri
    0.80
     Seriously
    0.78
    Ser
    0.72
    Seriously
    0.69
    Act Density 0.355%

    No Known Activations