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

    Neuronpedia

    INDEX
    Explanations

    numbers related to specific classes, locations, and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to age-related statistics or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.81
    chell
    -0.76
    nesday
    -0.72
    iya
    -0.72
    apeake
    -0.68
    uyomi
    -0.67
    achus
    -0.67
     tension
    -0.66
     Rebellion
    -0.65
    theless
    -0.64
    POSITIVE LOGITS
    328
    1.12
     ILCS
    1.10
    dfx
    0.87
    467
    0.81
    uthor
    0.80
    768
    0.79
    329
    0.78
    lav
    0.77
    327
    0.77
    630
    0.77
    Act Density 0.046%

    No Known Activations