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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs associated with deceitfulness or fraudulent behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.17
    3:0.04
    4:0.39
    5:0.04
    6:0.03
    7:0.03
    8:0.04
    9:0.08
    10:0.04
    11:0.03
    Negative Logits
     exha
    -1.28
     weighs
    -1.27
    vale
    -1.27
     Skydragon
    -1.24
     Racer
    -1.21
     THERE
    -1.21
     mosqu
    -1.21
     Stability
    -1.21
     Ribbon
    -1.19
    ���
    -1.19
    POSITIVE LOGITS
     omission
    1.82
    tein
    1.52
     deceit
    1.49
     deception
    1.41
    ousy
    1.39
    olester
    1.37
     dece
    1.34
     liar
    1.32
     dishonest
    1.32
    gery
    1.32
    Act Density 0.011%

    No Known Activations