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

    Neuronpedia

    INDEX
    Explanations

    words related to physical or emotional restraint

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Acad
    -0.74
    ynt
    -0.73
    dule
    -0.72
     dot
    -0.68
    ln
    -0.68
    mitt
    -0.67
    bsite
    -0.67
     Compos
    -0.67
     Kon
    -0.67
    ossier
    -0.66
    POSITIVE LOGITS
     restraint
    1.36
     restrain
    1.27
     restraints
    1.24
    raint
    1.10
     restraining
    1.00
     restrained
    0.95
     sidx
    0.91
    raints
    0.90
    estinal
    0.83
     necks
    0.81
    Act Density 0.008%

    No Known Activations