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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policy implications and enforcement in economic or legal contexts

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

    permission, allowance, or lack of restriction

    np_acts-logits-general · gemini-2.0-flash

    lack of restriction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.59
    ктан
    -0.53
    ophobic
    -0.51
    ThroughAttribute
    -0.51
     restrictive
    -0.48
     Shut
    -0.48
    ंदीखरीदारी
    -0.48
    WebElementEntity
    -0.48
    exclu
    -0.47
     excl
    -0.47
    POSITIVE LOGITS
     lax
    1.00
     lenient
    0.95
     loosen
    0.94
     permissive
    0.94
     unrestricted
    0.91
     freely
    0.87
     allowing
    0.85
     permis
    0.85
     unchecked
    0.85
     Allowing
    0.83
    Act Density 0.763%

    No Known Activations