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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.07
    3:0.07
    4:0.08
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.10
    Negative Logits
    aber
    -3.02
    bis
    -2.56
    isma
    -2.54
     bis
    -2.52
     subconscious
    -2.50
    beit
    -2.46
    ibu
    -2.43
    ifle
    -2.31
    DC
    -2.31
    ghai
    -2.29
    POSITIVE LOGITS
     Trainer
    3.29
     Sisters
    2.99
     Superintendent
    2.81
     Planned
    2.66
     VIDEOS
    2.61
     Secretary
    2.58
     Stephenson
    2.47
     Creator
    2.46
     Apostle
    2.46
     Strategy
    2.44
    Act Density 0.000%

    No Known Activations