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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.05
    2:0.10
    3:0.05
    4:0.04
    5:0.04
    6:0.25
    7:0.04
    8:0.03
    9:0.19
    10:0.04
    11:0.03
    Negative Logits
    VM
    -3.83
     Peters
    -3.78
    Interstitial
    -3.58
    ा
    -3.45
    efer
    -3.38
     Sterling
    -3.36
     Tib
    -3.34
     Farming
    -3.32
     Lincoln
    -3.31
     Farmer
    -3.20
    POSITIVE LOGITS
     Cool
    7.29
    Cool
    6.71
    cool
    6.67
     cool
    6.34
     cooler
    6.17
     cooling
    5.37
     coolest
    5.19
     cooled
    5.00
     chill
    4.59
     geek
    4.03
    Act Density 0.001%

    No Known Activations