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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations or code snippets

    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
    wcs
    -0.70
     breed
    -0.64
    ergy
    -0.64
    zynski
    -0.64
    eding
    -0.61
     establishment
    -0.61
    erning
    -0.61
     plateau
    -0.61
     braces
    -0.60
    emouth
    -0.60
    POSITIVE LOGITS
    ãĥīãĥ©ãĤ´ãĥ³
    1.04
    ãĤ¨ãĥ«
    0.94
    PsyNetMessage
    0.91
    CVE
    0.86
    ========
    0.85
    imm
    0.85
    76561
    0.83
    ãĥ´ãĤ¡
    0.83
    ãĤ½
    0.81
    true
    0.78
    Act Density 0.017%

    No Known Activations