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

    Neuronpedia

    INDEX
    Explanations

    words related to continuation or ongoing events

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "continue" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.85
    ramid
    -0.70
    acho
    -0.66
     puppies
    -0.65
    LCS
    -0.64
    eah
    -0.63
    ilded
    -0.63
    uffle
    -0.63
    lain
    -0.63
    footed
    -0.63
    POSITIVE LOGITS
    uations
    1.11
    uation
    1.08
    uously
    1.02
    uity
    0.97
    uing
    0.95
    uality
    0.94
    uous
    0.94
    uum
    0.90
    ental
    0.90
    ued
    0.86
    Act Density 0.011%

    No Known Activations