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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical restraints and confinement in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    being restrained or confined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italij
    -0.54
     desmotivaciones
    -0.53
     AspNetCore
    -0.53
     ilustracja
    -0.49
     koszulka
    -0.49
    -0.48
     titolata
    -0.48
     intensidad
    -0.47
     toimi
    -0.47
     interpretar
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.67
     handcuffs
    0.57
     handcu
    0.57
     prison
    0.53
     jail
    0.50
     tied
    0.46
     bind
    0.45
     cages
    0.45
     imprison
    0.45
     tube
    0.44
    Act Density 0.027%

    No Known Activations