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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "even" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urst
    -0.72
    ME
    -0.67
    adr
    -0.58
    west
    -0.58
     behalf
    -0.57
    sa
    -0.57
     Module
    -0.57
    dc
    -0.56
    orne
    -0.55
    erville
    -0.55
    POSITIVE LOGITS
     even
    3.12
    even
    2.36
     EVEN
    2.30
     Even
    1.49
    Even
    1.42
     especially
    1.37
     downright
    1.29
     despite
    1.16
    especially
    1.11
     indeed
    1.07
    Act Density 0.066%

    No Known Activations