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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical or mental restraint

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restraint or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dule
    -0.74
     dot
    -0.73
    mberg
    -0.71
    ln
    -0.70
    guyen
    -0.69
    ynt
    -0.68
    bsite
    -0.68
    ossier
    -0.68
     Acad
    -0.67
    pp
    -0.67
    POSITIVE LOGITS
     restraint
    1.28
    raint
    1.21
     restrain
    1.17
     restraints
    1.12
    raints
    0.97
     restraining
    0.95
     sidx
    0.91
    estinal
    0.86
     restrained
    0.86
    rained
    0.80
    Act Density 0.011%

    No Known Activations