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

    Neuronpedia

    INDEX
    Explanations

    references to physical screws or metaphorical uses of the word "screw"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "screw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.69
    acons
    -0.69
    leased
    -0.64
    omas
    -0.64
    govtrack
    -0.64
    porting
    -0.63
    iferation
    -0.63
    CHR
    -0.63
    hammad
    -0.63
    ve
    -0.62
    POSITIVE LOGITS
    driver
    1.21
     screw
    1.16
     screws
    1.15
    drivers
    0.92
    hole
    0.90
     Screw
    0.88
     screwed
    0.83
     Whedon
    0.79
    holes
    0.78
    picking
    0.74
    Act Density 0.007%

    No Known Activations