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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations or formal notations

    oai_token-act-pair · gpt-3.5-turbo

    mathematical equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.85
    eness
    -0.82
    itage
    -0.82
     nodd
    -0.78
    igating
    -0.76
    wright
    -0.73
    SPONSORED
    -0.71
    esis
    -0.70
    imony
    -0.67
    ovan
    -0.67
    POSITIVE LOGITS
    ========
    1.62
    ============
    1.50
    ===
    1.09
    ãĥīãĥ©ãĤ´ãĥ³
    0.83
     TRUE
    0.78
    ãĥ´ãĤ¡
    0.74
    ãĤ¨ãĥ«
    0.72
     False
    0.72
     FALSE
    0.71
     infinity
    0.68
    Act Density 0.021%

    No Known Activations