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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence or cessation of a certain action or condition

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases expressing limitations or the concept of "no more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irez
    -0.81
    hare
    -0.75
    BIT
    -0.74
    cius
    -0.73
    =-=-
    -0.70
    iao
    -0.67
    aday
    -0.67
    yip
    -0.67
    itime
    -0.66
    pherd
    -0.65
    POSITIVE LOGITS
     than
    0.88
    Fake
    0.76
    cial
    0.73
     excuses
    0.70
     ado
    0.69
     nor
    0.67
     whatsoever
    0.66
     pancakes
    0.63
    trace
    0.61
     pesky
    0.60
    Act Density 0.039%

    No Known Activations