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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    equations or comparisons involving numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.83
     nodd
    -0.80
    eness
    -0.78
    imony
    -0.75
    emouth
    -0.71
    iates
    -0.70
    Ãį
    -0.68
    iate
    -0.67
    soDeliveryDate
    -0.66
    evin
    -0.66
    POSITIVE LOGITS
    ========
    1.58
    ============
    1.37
    ===
    0.98
    ãĥīãĥ©ãĤ´ãĥ³
    0.87
    ãĤ¨ãĥ«
    0.68
    ãĥ´ãĤ¡
    0.65
     nil
    0.65
     False
    0.64
    eric
    0.64
     FALSE
    0.64
    Act Density 0.015%

    No Known Activations