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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements regarding quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.98
    andise
    -0.81
    allery
    -0.79
    vertisement
    -0.79
    hern
    -0.77
    merce
    -0.77
    undle
    -0.76
    ¶æ
    -0.74
    StreamerBot
    -0.73
    Ļ½
    -0.73
    POSITIVE LOGITS
     times
    1.53
     iterations
    1.09
     calories
    1.07
     hours
    1.05
     pounds
    1.01
     days
    1.00
     copies
    0.99
     acres
    0.98
     servings
    0.98
     gallons
    0.97
    Act Density 0.041%

    No Known Activations