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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "is" and variations of whitespace or spacing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.43
     itſelf
    -1.29
     myſelf
    -1.25
     iſt
    -1.24
     ་་
    -1.22
     ſche
    -1.21
     auffi
    -1.19
     againſt
    -1.18
    ſelf
    -1.16
    <bos>
    -1.15
    POSITIVE LOGITS
     
    1.62
     "
    0.87
     $
    0.84
     K
    0.81
     T
    0.81
     C
    0.80
     “
    0.79
     L
    0.78
     D
    0.78
     S
    0.77
    Act Density 1.761%

    No Known Activations