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

    Neuronpedia

    INDEX
    Explanations

    words related to physical or behavioral restriction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "restraint" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onymous
    -0.74
    dule
    -0.74
    olog
    -0.73
    eday
    -0.71
    ovych
    -0.71
    nexus
    -0.69
     Blessed
    -0.69
    mberg
    -0.66
    ynt
    -0.65
    mitt
    -0.65
    POSITIVE LOGITS
     restraint
    1.00
    raint
    0.97
     restraints
    0.94
    raints
    0.93
    estinal
    0.92
     restrain
    0.85
     restraining
    0.76
    encies
    0.75
     actionGroup
    0.75
     breathing
    0.74
    Act Density 0.021%

    No Known Activations