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

    Neuronpedia

    INDEX
    Explanations

    arithmetic operations, particularly subtraction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to arithmetic operations, specifically subtraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zimmer
    -0.78
    CLUD
    -0.71
     Wiggins
    -0.70
    BE
    -0.70
    ãĥīãĥ©
    -0.70
    papers
    -0.69
     Cosby
    -0.68
    Accessory
    -0.67
    HOME
    -0.67
    JM
    -0.64
    POSITIVE LOGITS
    raction
    1.26
    itled
    1.15
     subt
    1.07
    racted
    1.05
    weet
    1.03
    ript
    1.02
    lest
    1.01
    leness
    1.00
    rop
    0.99
    inguished
    0.98
    Act Density 0.010%

    No Known Activations