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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "even"

    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
    -0.97
    asus
    -0.88
    aim
    -0.83
    cel
    -0.75
    othy
    -0.74
    idem
    -0.73
    obi
    -0.73
    ugal
    -0.72
    scribe
    -0.72
    acker
    -0.71
    POSITIVE LOGITS
     though
    1.07
     tho
    0.95
     remotely
    0.93
     mentioning
    0.72
     indirectly
    0.69
    handedly
    0.69
     worse
    0.69
    handed
    0.69
     joking
    0.67
     moderately
    0.66
    Act Density 0.041%

    No Known Activations