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

    Neuronpedia

    INDEX
    Explanations

    references to fractions or ratios in numeric expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]).
    -0.64
     }}"></
    -0.62
    "},
    -0.59
    }));
    -0.58
    runApp
    -0.57
    ษัท
    -0.56
    "])
    -0.56
    ofern
    -0.56
    ")).
    -0.55
    '},
    -0.55
    POSITIVE LOGITS
     thousands
    0.74
     hundreds
    0.73
     Hundreds
    0.73
     Thousands
    0.72
    Thousands
    0.70
    hundreds
    0.69
    undred
    0.68
    Hundreds
    0.67
     typelib
    0.67
    Datuak
    0.66
    Act Density 0.302%

    No Known Activations