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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of locations or organizations in official contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /"
    -0.78
    udder
    -0.72
    ?).
    -0.72
    —"
    -0.70
    cum
    -0.70
    ?),
    -0.70
    ="/
    -0.69
    ___
    -0.68
    Adds
    -0.68
    pless
    -0.67
    POSITIVE LOGITS
    resa
    1.08
     importance
    1.00
     integrity
    1.00
     totality
    0.99
     seriousness
    0.98
     utmost
    0.97
     slightest
    0.95
     timing
    0.94
     intention
    0.93
     urgency
    0.93
    Act Density 0.294%

    No Known Activations