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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty or lack of control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.05
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.31
    7:0.03
    8:0.02
    9:0.06
    10:0.06
    11:0.26
    Negative Logits
     Nelson
    -2.86
     Moons
    -2.74
    wine
    -2.74
     Kaine
    -2.72
     Stone
    -2.69
     Forth
    -2.62
     Richmond
    -2.60
     Strange
    -2.60
    ,)
    -2.59
    imp
    -2.59
    POSITIVE LOGITS
    �
    4.52
    ¨
    3.58
    »
    3.52
    �
    3.25
    ´
    3.20
    cffffcc
    3.20
    ?」
    3.19
    」
    3.18
    ・
    3.09
    ּ
    3.02
    Act Density 0.292%

    No Known Activations