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

    Neuronpedia

    INDEX
    Explanations

    the word "even"

    oai_token-act-pair · gpt-3.5-turbo

    the recurring use of the word "even"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.80
    taboola
    -0.70
    essee
    -0.69
    ĺħ
    -0.67
    gered
    -0.65
    arnaev
    -0.64
    Enlarge
    -0.64
    llo
    -0.63
    ãĤ´ãĥ³
    -0.61
    acker
    -0.61
    POSITIVE LOGITS
     rudimentary
    1.07
     modest
    1.03
    handedly
    1.01
     moderately
    1.01
    handed
    0.99
     though
    0.94
     curs
    0.93
     mildly
    0.92
     minor
    0.90
     slight
    0.89
    Act Density 0.054%

    No Known Activations