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

    Neuronpedia

    INDEX
    Explanations

    references to identifying the source of evidence or information in a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    -0.78
    脚注の使い方
    -0.73
     חיצוניים
    -0.71
     himo
    -0.70
    WebVitals
    -0.69
     للمعارف
    -0.68
    issauga
    -0.68
     bezeichneter
    -0.67
    AndEndTag
    -0.66
    +#+
    -0.63
    POSITIVE LOGITS
     intentos
    0.47
     lo
    0.47
     tepat
    0.45
    principalTable
    0.45
     émer
    0.44
     neige
    0.44
     terminé
    0.44
     именно
    0.43
     порядке
    0.43
     humanas
    0.43
    Act Density 0.285%

    No Known Activations