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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "trivial" and its derivatives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Rai
    -0.70
    GOTREF
    -0.63
    kuuta
    -0.62
     Neuer
    -0.59
    charts
    -0.58
    ker
    -0.58
    y
    -0.57
    ●●
    -0.57
     Kante
    -0.56
    su
    -0.56
    POSITIVE LOGITS
    trivial
    1.47
     trivial
    1.25
     trivi
    1.13
    rivial
    1.13
    monials
    0.92
     trivia
    0.88
     ostavi
    0.84
     Trivia
    0.83
    Aiheesta
    0.81
     trif
    0.81
    Act Density 0.003%

    No Known Activations