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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions related to the handling or use of handcuffs

    oai_token-act-pair · gpt-3.5-turbo

    references to handcuffing and restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynt
    -0.75
     Destination
    -0.72
    GY
    -0.71
    soType
    -0.67
    Gs
    -0.66
     Schwarz
    -0.64
    finder
    -0.64
    gal
    -0.63
     Reasons
    -0.63
    ogh
    -0.63
    POSITIVE LOGITS
     handcuffed
    1.16
     shack
    1.09
     strapped
    1.05
     handcuffs
    1.04
     handc
    1.03
     cuff
    0.87
     clasp
    0.87
     straps
    0.86
     confinement
    0.85
     chained
    0.84
    Act Density 0.023%

    No Known Activations