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

    Neuronpedia

    INDEX
    Explanations

    concepts related to confinement and social constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Criterion
    -0.14
     priority
    -0.14
    efa
    -0.14
    registry
    -0.14
    ipop
    -0.14
     forgiving
    -0.14
    KO
    -0.13
    Priority
    -0.13
     recep
    -0.13
     disturbed
    -0.13
    POSITIVE LOGITS
     restriction
    0.34
     confines
    0.34
     confinement
    0.33
     restrictions
    0.33
     restricted
    0.32
    restriction
    0.30
     Restricted
    0.30
     restrict
    0.30
     limitation
    0.29
     Restrictions
    0.28
    Act Density 0.216%

    No Known Activations