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

    instances of the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.91
    idelines
    -0.83
    rarily
    -0.74
    ciplinary
    -0.74
    othy
    -0.73
    creen
    -0.73
    emp
    -0.72
    aper
    -0.70
    raud
    -0.69
    opian
    -0.69
    POSITIVE LOGITS
     though
    0.77
     remotely
    0.73
     seasoned
    0.66
     mundane
    0.65
    handed
    0.62
     tho
    0.61
     Admir
    0.59
     moderately
    0.58
     curs
    0.58
     reputable
    0.58
    Act Density 0.053%

    No Known Activations