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

    Neuronpedia

    INDEX
    Explanations

    words related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to importance and urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rity
    -0.83
    ancies
    -0.82
    ramids
    -0.80
    adders
    -0.79
    istries
    -0.77
     chambers
    -0.77
    ignt
    -0.76
    azines
    -0.75
    apons
    -0.75
    poons
    -0.75
    POSITIVE LOGITS
     breaker
    0.88
     starter
    0.86
     deterrent
    0.85
     unto
    0.84
     unless
    0.80
     punishable
    0.76
     occurrence
    0.75
     because
    0.75
    stay
    0.75
     anymore
    0.75
    Act Density 0.195%

    No Known Activations