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

    Neuronpedia

    INDEX
    Explanations

    the word "real" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "real" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.98
    theless
    -0.88
    mph
    -0.84
    hire
    -0.81
     Carbuncle
    -0.76
    avorite
    -0.76
     Supported
    -0.74
    attery
    -0.72
    acks
    -0.71
    azard
    -0.70
    POSITIVE LOGITS
    ignment
    1.20
     estate
    1.15
    isation
    1.01
    polit
    0.98
     culprit
    0.98
    igned
    0.97
    igning
    0.95
    izations
    0.82
     Estate
    0.82
     thing
    0.82
    Act Density 0.019%

    No Known Activations