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

    Neuronpedia

    INDEX
    Explanations

    references to a particular type or brand of technology or software called "PI."

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular metric or index related to performance, likely in sports or competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    suit
    -1.01
    spread
    -0.88
    ships
    -0.88
    grounds
    -0.84
    ding
    -0.83
    tones
    -0.80
    space
    -0.79
    size
    -0.79
    sword
    -0.78
    sound
    -0.78
    POSITIVE LOGITS
    KA
    0.98
    OGR
    0.89
    Äĩ
    0.87
    KE
    0.86
    KK
    0.85
    URE
    0.85
    cture
    0.84
    ZZ
    0.84
    PI
    0.83
    odcast
    0.83
    Act Density 0.016%

    No Known Activations