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
    2:0.09
    3:0.09
    4:0.07
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
     Corpus
    -3.00
    �
    -2.71
    )|
    -2.64
     GOODMAN
    -2.58
    AMY
    -2.53
     finance
    -2.49
    =>
    -2.48
    ع
    -2.45
     =>
    -2.43
    .","
    -2.41
    POSITIVE LOGITS
    warm
    2.72
    buck
    2.69
     Witches
    2.63
     Wizards
    2.57
    Slot
    2.57
     Shank
    2.56
     basket
    2.55
     baskets
    2.53
     Gat
    2.51
     Gan
    2.50
    Act Density 0.000%

    No Known Activations