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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs related to knowledge or understanding

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate knowledge or awareness of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ermanent
    -0.85
    phabet
    -0.84
    epend
    -0.72
    ciation
    -0.66
    idav
    -0.65
    ciating
    -0.65
    osures
    -0.64
    eworthy
    -0.64
    ankind
    -0.63
    amaz
    -0.63
    POSITIVE LOGITS
    ledged
    0.82
     Clause
    0.69
    edge
    0.64
     instinctively
    0.64
     Curve
    0.64
    iencies
    0.63
     weakness
    0.62
    ibly
    0.61
    ãĤ¨ãĥ«
    0.60
    quickShipAvailable
    0.59
    Act Density 0.346%

    No Known Activations