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

    Neuronpedia

    INDEX
    Explanations

    the Ċ symbol

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence structure indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     analys
    -0.97
     metic
    -0.95
     derog
    -0.89
     phenomen
    -0.88
     foc
    -0.87
     predis
    -0.86
     massively
    -0.85
    ©¶æ
    -0.85
     caus
    -0.84
     suppressed
    -0.84
    POSITIVE LOGITS
    Residents
    1.85
    Officials
    1.74
    Mayor
    1.73
    Copyright
    1.72
    Owner
    1.70
    Council
    1.65
    Neigh
    1.63
    Crew
    1.63
    City
    1.62
    Contact
    1.62
    Act Density 0.353%

    No Known Activations