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

    Neuronpedia

    INDEX
    Explanations

    phrases related to allowance and flexibility in various contexts

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

    allowing permission or freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ércoles
    -0.34
    ohist
    -0.34
    cuál
    -0.33
     FormData
    -0.33
    XmlElement
    -0.32
    Demografía
    -0.31
     Schol
    -0.31
    cientes
    -0.31
    phin
    -0.31
    Unsubscribe
    -0.30
    POSITIVE LOGITS
     allowed
    1.26
     Allowed
    1.24
     allow
    1.21
    Allowed
    1.17
     Allow
    1.16
     allows
    1.14
    allow
    1.13
    allowed
    1.13
    Allow
    1.09
     ALLOWED
    1.09
    Act Density 0.049%

    No Known Activations