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

    Neuronpedia

    INDEX
    Explanations

    fractions and measurements in recipes or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.68
    addCriterion
    -0.68
    okovic
    -0.67
    NameInMap
    -0.66
    estacks
    -0.65
    toHaveBeenCalled
    -0.64
     createSprite
    -0.64
    giarism
    -0.64
    achuca
    -0.63
    ulemon
    -0.63
    POSITIVE LOGITS
     tercio
    0.83
     Quarter
    0.82
     quarter
    0.80
     fraction
    0.80
    quarter
    0.77
    Quarter
    0.74
    ⅓
    0.73
     QUARTER
    0.73
    fraction
    0.72
     ¼
    0.72
    Act Density 0.177%

    No Known Activations