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

    Neuronpedia

    INDEX
    Explanations

    numerical data and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.75
    anism
    -0.71
    ModLoader
    -0.71
    lich
    -0.70
    Accessory
    -0.69
    emis
    -0.67
    osi
    -0.65
    odor
    -0.64
    sic
    -0.63
    raught
    -0.63
    POSITIVE LOGITS
     compiled
    0.93
    heet
    0.92
     grap
    0.89
     tallied
    0.88
     illustrating
    0.85
     fluct
    0.83
    metry
    0.81
     indicate
    0.81
     quoted
    0.79
     showing
    0.78
    Act Density 0.096%

    No Known Activations