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

    Neuronpedia

    INDEX
    Explanations

    plural nouns and their associated forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.20
    3:0.08
    4:0.09
    5:0.06
    6:0.15
    7:0.06
    8:0.06
    9:0.03
    10:0.09
    11:0.08
    Negative Logits
     loophole
    -1.55
     fallacy
    -1.50
     iod
    -1.41
     lightsaber
    -1.39
     silence
    -1.38
     pow
    -1.38
     gust
    -1.36
     omission
    -1.35
     Suzuki
    -1.33
     brakes
    -1.33
    POSITIVE LOGITS
    insured
    1.96
    excluding
    1.74
    inion
    1.73
    wealth
    1.67
    uliffe
    1.64
    interrupted
    1.62
    anguard
    1.60
    etheless
    1.59
    ngth
    1.58
    mort
    1.57
    Act Density 0.011%

    No Known Activations