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

    Neuronpedia

    INDEX
    Explanations

    amounts or measurements specified in grams or milligrams

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to food ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    learn
    -0.75
     skelet
    -0.74
     fundament
    -0.68
     timetable
    -0.66
     obser
    -0.64
     challeng
    -0.64
     Debor
    -0.63
     Doodle
    -0.63
     neighb
    -0.63
    Reviewer
    -0.63
    POSITIVE LOGITS
    arettes
    0.86
     apiece
    0.83
    hz
    0.82
    onz
    0.79
     bottles
    0.78
     servings
    0.77
    reens
    0.77
    pm
    0.76
    omez
    0.75
    Quantity
    0.74
    Act Density 0.026%

    No Known Activations