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

    Neuronpedia

    INDEX
    Explanations

    words related to something going beyond its usual limits or exceeding expectations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to transcending limitations or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ches
    -0.66
    liest
    -0.66
    eers
    -0.65
    gage
    -0.65
     Falcons
    -0.63
    ÙIJ
    -0.63
    pring
    -0.62
    Reviewer
    -0.62
    igan
    -0.62
    igans
    -0.61
    POSITIVE LOGITS
    ental
    0.95
    ribed
    0.94
    ophon
    0.90
    racted
    0.89
    inant
    0.84
    oded
    0.83
    odies
    0.83
    ingu
    0.79
    inct
    0.78
    rypted
    0.77
    Act Density 0.023%

    No Known Activations