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

    Neuronpedia

    INDEX
    Explanations

    negative symbols and phrases indicating disapproval or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.31
    2:0.03
    3:0.18
    4:0.04
    5:0.08
    6:0.05
    7:0.05
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    UGE
    -2.50
    entimes
    -2.48
     earthqu
    -2.32
     skewed
    -2.14
     mistaken
    -2.11
    OOL
    -2.11
     indistinguishable
    -2.07
     taller
    -2.06
    inged
    -2.06
     longer
    -2.05
    POSITIVE LOGITS
    shall
    3.50
    23
    2.84
    bye
    2.73
    ratulations
    2.72
    iae
    2.70
    conduct
    2.68
    22
    2.66
    25
    2.55
    28
    2.51
    hew
    2.46
    Act Density 0.001%

    No Known Activations