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

    Neuronpedia

    INDEX
    Explanations

    comparisons or emphasis using the word "even"

    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
    emp
    -0.78
    ected
    -0.71
    ========
    -0.71
    onomous
    -0.69
    ãĥ¼ãĥ³
    -0.68
    ãĤ´ãĥ³
    -0.66
    utra
    -0.65
    ugal
    -0.65
    warts
    -0.65
    aryl
    -0.63
    POSITIVE LOGITS
    handed
    1.28
     worse
    1.21
     hotter
    1.20
     sharper
    1.18
     tougher
    1.16
     clearer
    1.14
     harder
    1.14
     nicer
    1.14
     bigger
    1.13
     greater
    1.13
    Act Density 0.053%

    No Known Activations