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

    Neuronpedia

    INDEX
    Explanations

    references to covert and overt illegal or deceptive activities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    AndFlush
    -0.65
     surla
    -0.62
     '\\;'
    -0.59
     ennemis
    -0.57
    ("")]
    -0.56
    ifndef
    -0.54
     ISTAT
    -0.54
     nemici
    -0.54
    FXMLLoader
    -0.53
    razor
    -0.53
    POSITIVE LOGITS
     overt
    2.22
     blatant
    1.77
     covert
    1.56
     overtly
    1.33
     conspicuous
    1.28
     blatantly
    1.28
     flagrant
    1.27
     rampant
    1.15
     brazen
    1.05
     conspicuously
    0.94
    Act Density 0.004%

    No Known Activations