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

    Neuronpedia

    INDEX
    Explanations

    mentions of the specific name "Waters"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the filmmaker John Waters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.84
    PsyNetMessage
    -0.74
    ient
    -0.74
     Canucks
    -0.68
     ger
    -0.67
    arin
    -0.67
    Jun
    -0.64
     imperfect
    -0.63
    UG
    -0.63
    NET
    -0.63
    POSITIVE LOGITS
     Waters
    2.61
     Stevenson
    1.50
     slaughter
    1.37
    waters
    1.36
     Owens
    1.27
     Wick
    1.24
     Slaughter
    1.24
     Wool
    1.10
     Meat
    1.05
     Heller
    1.04
    Act Density 0.039%

    No Known Activations