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

    Neuronpedia

    INDEX
    Explanations

    references to classified information or security breaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.20
    1:0.02
    2:0.19
    3:0.11
    4:0.03
    5:0.11
    6:0.02
    7:0.06
    8:0.11
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    nesday
    -2.78
    ogie
    -2.65
    iatus
    -2.55
    ourney
    -2.54
     Paleo
    -2.53
     Rally
    -2.51
     Comedy
    -2.50
     Ven
    -2.43
     Taste
    -2.40
    Beer
    -2.39
    POSITIVE LOGITS
     declass
    5.32
     classified
    4.47
    classified
    4.22
     classification
    3.97
     encryption
    3.50
     Classification
    3.26
    CLASSIFIED
    3.15
     classify
    3.06
     espionage
    2.98
     redacted
    2.96
    Act Density 0.014%

    No Known Activations