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

    Neuronpedia

    INDEX
    Explanations

    possessive forms or contractions of the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    воÑĢ
    -0.15
     наÑĢ
    -0.14
    uat
    -0.13
    воÑİ
    -0.13
    ewater
    -0.13
    ville
    -0.13
     bestimm
    -0.12
    thon
    -0.12
    these
    -0.12
    arrow
    -0.12
    POSITIVE LOGITS
     how
    0.31
     where
    0.30
     what
    0.29
     why
    0.27
     hoping
    0.26
     another
    0.26
     a
    0.23
     an
    0.23
     my
    0.23
     something
    0.21
    Act Density 0.028%

    No Known Activations