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

    Neuronpedia

    INDEX
    Explanations

    words related to subtraction or removal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subtraction and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zimmer
    -0.80
    papers
    -0.77
    ãĥīãĥ©
    -0.73
    BE
    -0.72
    USE
    -0.69
    ITNESS
    -0.68
     Fast
    -0.68
     Commodore
    -0.68
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
     Wiggins
    -0.67
    POSITIVE LOGITS
     subt
    1.49
    itled
    1.14
    raction
    1.11
    otal
    1.09
    inguished
    1.02
    racted
    1.01
    rop
    1.00
    weet
    0.97
    lest
    0.95
    leness
    0.94
    Act Density 0.008%

    No Known Activations