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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and numerical relationships

    oai_token-act-pair · gpt-3.5-turbo

    the equals sign used in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.86
    eness
    -0.83
    emouth
    -0.76
    imony
    -0.75
     nodd
    -0.74
    alis
    -0.65
    wright
    -0.64
    unia
    -0.63
    wcs
    -0.63
    soDeliveryDate
    -0.63
    POSITIVE LOGITS
    ========
    1.62
    ============
    1.42
    ===
    1.11
    ãĥīãĥ©ãĤ´ãĥ³
    0.86
    ãĥ´ãĤ¡
    0.72
     TRUE
    0.69
    ãĤ¨ãĥ«
    0.69
    unknown
    0.68
     FALSE
    0.67
     False
    0.67
    Act Density 0.016%

    No Known Activations