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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.68
     Current
    -0.68
     Submit
    -0.67
    has
    -0.65
    onic
    -0.64
     Extend
    -0.64
    arta
    -0.63
    ociate
    -0.63
     Expand
    -0.62
    continue
    -0.62
    POSITIVE LOGITS
     unclear
    1.11
     raining
    1.06
    nt
    0.92
     impossible
    0.91
     easier
    0.87
     inevitable
    0.87
     easy
    0.86
    hers
    0.84
     evident
    0.81
     definitely
    0.81
    Act Density 0.101%

    No Known Activations