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

    Neuronpedia

    INDEX
    Explanations

    the word "even" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" in various contexts, suggesting it looks for expressions that indicate unexpectedness or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.89
    olate
    -0.73
    othy
    -0.71
    HCR
    -0.70
    reating
    -0.70
    cel
    -0.65
    aim
    -0.65
    È
    -0.65
    ync
    -0.65
    perate
    -0.65
    POSITIVE LOGITS
    handed
    0.99
     though
    0.90
     remotely
    0.89
    handedly
    0.85
     tho
    0.80
    ivari
    0.67
    este
    0.67
     numbered
    0.66
    flo
    0.65
    âĹ¼
    0.62
    Act Density 0.048%

    No Known Activations