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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security regulations and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SKF
    -0.15
    EMON
    -0.15
    Anchor
    -0.15
    ensus
    -0.15
     Anchor
    -0.14
    iol
    -0.14
    ervoir
    -0.14
    antar
    -0.14
    è£Ĥ
    -0.14
    tribution
    -0.14
    POSITIVE LOGITS
     TSA
    0.39
     screening
    0.38
     security
    0.35
     airport
    0.34
     Screening
    0.34
     screenings
    0.33
     screen
    0.32
    -screen
    0.31
     Security
    0.31
     Airport
    0.30
    Act Density 0.044%

    No Known Activations