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

    Neuronpedia

    INDEX
    Explanations

    references to quantity or repetition, particularly with the word "more"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.05
     raiſ
    -0.96
     ſtill
    -0.90
     paſſ
    -0.89
     ſtand
    -0.89
     Reſ
    -0.88
     myſelf
    -0.88
     faſt
    -0.88
     Eſ
    -0.87
     anſ
    -0.86
    POSITIVE LOGITS
     @"
    0.68
     more
    0.62
    (@"
    0.57
    expects
    0.55
     confronting
    0.54
    ***********/
    0.52
     
    0.52
    \{\\
    0.50
    @"
    0.48
    BlockPos
    0.48
    Act Density 0.234%

    No Known Activations