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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical or ordinal significance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ha
    -0.42
    pagni
    -0.37
     diperoleh
    -0.36
     estrenar
    -0.35
     R
    -0.35
     witness
    -0.35
     высота
    -0.34
     bien
    -0.34
    ENH
    -0.34
     confronti
    -0.33
    POSITIVE LOGITS
    OGND
    0.98
     Мексичка
    0.91
     Monfieur
    0.91
     Majefty
    0.88
    Билгалдахарш
    0.86
     ſever
    0.84
    #+#
    0.83
     iſt
    0.82
    WebVitals
    0.82
     Anſ
    0.82
    Act Density 0.204%

    No Known Activations