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

    Neuronpedia

    INDEX
    Explanations

    contractions of words

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "I've"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapt
    -0.74
     Skydragon
    -0.66
    é¾įå¥ij士
    -0.61
     owl
    -0.59
     scoreboard
    -0.59
     jud
    -0.58
    Reviewer
    -0.57
    ological
    -0.56
     keywords
    -0.55
     separ
    -0.55
    POSITIVE LOGITS
    tta
    0.96
    mber
    0.90
    theless
    0.87
    tt
    0.87
     Been
    0.86
     been
    0.86
    ttes
    0.86
    tti
    0.85
    been
    0.85
    ggies
    0.84
    Act Density 0.028%

    No Known Activations