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

    Neuronpedia

    INDEX
    Explanations

    descriptions or actions involving handcuffing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restraints, specifically handcuffs and similar concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aer
    -0.71
    reading
    -0.71
    GY
    -0.69
    vals
    -0.65
    Ale
    -0.65
    soType
    -0.65
     Destination
    -0.63
    esters
    -0.62
    yll
    -0.62
    RT
    -0.62
    POSITIVE LOGITS
     handcuffed
    1.38
     handc
    1.05
     shack
    0.94
     chained
    0.86
     clipping
    0.85
     handcuffs
    0.85
     restrain
    0.84
     strapped
    0.83
     cuff
    0.80
     clen
    0.76
    Act Density 0.015%

    No Known Activations