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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical probabilities involving letters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Piston
    -0.68
    ValueStyle
    -0.68
    ussis
    -0.65
    WebVitals
    -0.61
     gyhoeddwyd
    -0.59
     poppy
    -0.58
     venons
    -0.58
     epist
    -0.57
     يتيمه
    -0.57
     незавершена
    -0.57
    POSITIVE LOGITS
    phem
    0.57
     PRET
    0.54
     حد
    0.53
    weiler
    0.49
     graça
    0.48
    werth
    0.48
    likon
    0.47
     sola
    0.47
     pretty
    0.47
    ifoli
    0.47
    Act Density 0.002%

    No Known Activations