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

    Neuronpedia

    INDEX
    Explanations

    the probability of selecting specific combinations of letters in a sampling process

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     letter
    -1.75
    letter
    -1.64
    Letter
    -1.60
     Letter
    -1.53
     LETTER
    -1.52
    LETTER
    -1.37
     lettre
    -0.96
    出版年
    -0.93
     lettera
    -0.87
     للاسماء
    -0.86
    POSITIVE LOGITS
     letters
    0.84
     destaque
    0.57
     letras
    0.56
    TagHelpers
    0.56
     lettres
    0.53
     Letters
    0.52
     起
    0.48
    ziehung
    0.45
     mundos
    0.45
    Letters
    0.44
    Act Density 0.007%

    No Known Activations