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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and terms that indicate entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lives
    -1.07
     Accountability
    -1.04
     Lines
    -1.00
     Blocks
    -0.98
     Lover
    -0.95
     Characters
    -0.93
     Clause
    -0.93
     Away
    -0.91
     Thing
    -0.91
     Ones
    -0.91
    POSITIVE LOGITS
     tv
    0.79
     franc
    0.76
     democr
    0.75
     commons
    0.74
    ensis
    0.73
    fortunately
    0.73
     academy
    0.72
    arians
    0.71
     united
    0.70
     republican
    0.69
    Act Density 0.767%

    No Known Activations