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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or named entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.76
    onic
    -0.69
     Submit
    -0.67
     Current
    -0.67
    has
    -0.66
    arta
    -0.66
     LAT
    -0.63
    Make
    -0.62
    stand
    -0.62
     Extend
    -0.61
    POSITIVE LOGITS
     unclear
    1.19
     raining
    1.06
     impossible
    0.99
     inevitable
    0.95
     easier
    0.89
     imperative
    0.88
     evident
    0.88
     worth
    0.87
     rumored
    0.87
     fortunate
    0.87
    Act Density 0.089%

    No Known Activations