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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.07
    4:0.08
    5:0.09
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
     Marxism
    -2.82
     oxid
    -2.78
     weld
    -2.68
     jQuery
    -2.64
     feminism
    -2.60
     unavoid
    -2.59
     cumbers
    -2.56
    acebook
    -2.56
     degrade
    -2.51
     RV
    -2.50
    POSITIVE LOGITS
     Cast
    2.98
    ouch
    2.93
     Spells
    2.82
     Bow
    2.69
     Song
    2.62
     Geh
    2.58
    isl
    2.56
     Cups
    2.48
    Has
    2.48
    inges
    2.46
    Act Density 0.000%

    No Known Activations