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

    Neuronpedia

    INDEX
    Explanations

    fractions or ratios in numerical context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.73
     nakalista
    -0.71
     Boyce
    -0.67
    tonsoft
    -0.67
     Cowell
    -0.67
     Grossman
    -0.66
     Verso
    -0.66
    zepine
    -0.66
     StringVar
    -0.65
    Халык
    -0.64
    POSITIVE LOGITS
    <<"\
    0.49
    upyter
    0.47
    ("'"
    0.45
    setDo
    0.43
    <bos>
    0.43
    日閲覧
    0.42
    ันท
    0.42
    //~
    0.42
    Jan
    0.42
    sibilidade
    0.42
    Act Density 0.008%

    No Known Activations