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

    Neuronpedia

    INDEX
    Explanations

    assertive commands or expressions related to silencing others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.53
    الحياه
    -0.50
    bitField
    -0.50
    RegressionTest
    -0.50
    ctools
    -0.50
    getSupport
    -0.49
    Tembelea
    -0.49
    RemoveField
    -0.48
    LElement
    -0.48
     Fad
    -0.47
    POSITIVE LOGITS
     silence
    1.08
     silent
    1.03
     silenced
    0.98
     Silence
    0.93
    Silence
    0.93
     mouth
    0.92
    silence
    0.92
     mouths
    0.90
    Shut
    0.88
    silent
    0.87
    Act Density 0.183%

    No Known Activations