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

    Neuronpedia

    INDEX
    Explanations

    the word "even" occurring within sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.82
    aim
    -0.75
    acker
    -0.73
    aser
    -0.70
    arnaev
    -0.70
    notations
    -0.69
    essee
    -0.69
    ãĤ´ãĥ³
    -0.69
    Shape
    -0.67
    ffen
    -0.66
    POSITIVE LOGITS
     though
    1.05
    handedly
    1.03
     tho
    0.98
     remotely
    0.98
    handed
    0.97
     moderately
    0.92
     if
    0.91
     rudimentary
    0.89
     mundane
    0.83
     slightest
    0.83
    Act Density 0.064%

    No Known Activations