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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "real" and discussions about what is genuine or authentic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hire
    -0.90
    azard
    -0.83
    utics
    -0.78
    zy
    -0.77
    xual
    -0.76
    azel
    -0.74
    avorite
    -0.74
    emi
    -0.74
    theless
    -0.73
    mph
    -0.72
    POSITIVE LOGITS
     culprit
    1.01
    ignment
    0.95
     estate
    0.89
    isation
    0.87
     brunt
    0.83
     truth
    0.78
    igned
    0.77
     thing
    0.77
     impetus
    0.77
     embodiment
    0.76
    Act Density 0.055%

    No Known Activations