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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically focusing on names such as "Stephen" with varying degrees of importance or infamy

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Stephen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -1.06
    footed
    -0.77
     circ
    -0.74
    engers
    -0.73
    igi
    -0.72
    LOAD
    -0.71
     guiActiveUnfocused
    -0.69
    mented
    -0.67
    fet
    -0.66
    exempt
    -0.65
    POSITIVE LOGITS
     Hawking
    1.28
     Paddock
    1.08
     Colbert
    0.99
    son
    0.89
    ology
    0.88
     Fry
    0.87
    ases
    0.85
     Strange
    0.83
     Stras
    0.83
     Harper
    0.82
    Act Density 0.016%

    No Known Activations