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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cabec
    -0.71
     Ried
    -0.68
    __':
    -0.68
    uillez
    -0.67
    oneofs
    -0.66
     Kanu
    -0.65
    --]
    -0.65
     collusion
    -0.64
    *****/
    -0.64
    TacToe
    -0.64
    POSITIVE LOGITS
     even
    1.66
    Even
    1.54
     Even
    1.52
    even
    1.46
    EVEN
    1.37
     EVEN
    1.35
    Даже
    1.25
     Даже
    1.19
    Mesmo
    1.12
     Incluso
    1.08
    Act Density 0.085%

    No Known Activations