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

    Neuronpedia

    INDEX
    Explanations

    references to scientific authors or collaborators, particularly in the context of publications or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.52
     ele
    -0.49
     he
    -0.48
     `
    -0.47
    aume
    -0.46
     ''
    -0.46
     **
    -0.46
     trä
    -0.45
    ndar
    -0.45
    dhan
    -0.45
    POSITIVE LOGITS
     CURIAM
    1.01
    évaluateur
    0.93
     دیکھیے
    0.82
    bewerken
    0.81
    #+#
    0.81
    脚注の使い方
    0.80
    发表于
    0.78
     estimés
    0.77
    MLLoader
    0.77
     >=",
    0.76
    Act Density 0.072%

    No Known Activations