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

    Neuronpedia

    INDEX
    Explanations

    words related to the brain and its functions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dialog
    -0.71
     Bundy
    -0.69
     FANTASY
    -0.67
    adoes
    -0.65
     Yanuk
    -0.64
     Friendship
    -0.63
     Arabian
    -0.63
    risome
    -0.63
    raviolet
    -0.62
     Seller
    -0.61
    POSITIVE LOGITS
    stem
    1.20
    washed
    1.03
    wash
    1.02
    washing
    0.92
    iac
    0.88
    fuck
    0.86
    waves
    0.85
     anatomy
    0.81
     brain
    0.80
    brain
    0.79
    Act Density 0.016%

    No Known Activations