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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to repetition or recurring actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeated" or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ect
    -0.70
    source
    -0.67
    inks
    -0.67
    oult
    -0.66
    iant
    -0.65
    tainment
    -0.64
    tain
    -0.63
    iors
    -0.63
    ift
    -0.62
     Limit
    -0.61
    POSITIVE LOGITS
     repeated
    3.78
     repeats
    1.98
     repeat
    1.95
     repeating
    1.88
    repe
    1.85
     repetition
    1.82
     repetitive
    1.55
     prolonged
    1.52
    repeat
    1.44
     reiterated
    1.44
    Act Density 0.018%

    No Known Activations