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

    Neuronpedia

    INDEX
    Explanations

    professions, expertise, and areas of importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significance or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cobb
    -0.69
     Wraith
    -0.61
     Doomsday
    -0.59
     caval
    -0.59
    RANT
    -0.59
     awa
    -0.57
     Camden
    -0.57
     Viper
    -0.56
     BMC
    -0.56
     Raw
    -0.55
    POSITIVE LOGITS
     proportions
    0.78
     fame
    0.71
    mods
    0.69
    chuk
    0.67
    yout
    0.67
    interest
    0.66
    lain
    0.65
     persuasion
    0.64
    farious
    0.64
    interstitial
    0.63
    Act Density 0.257%

    No Known Activations