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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "was" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mountains
    -0.69
     newsletters
    -0.67
    stood
    -0.65
    arta
    -0.62
     Millions
    -0.62
    Footnote
    -0.60
     HAVE
    -0.60
     conventions
    -0.60
    holders
    -0.59
     IMAGES
    -0.59
    POSITIVE LOGITS
    hes
    1.31
    wolves
    1.00
     originally
    0.98
    hers
    0.94
    wolf
    0.92
    nt
    0.90
     born
    0.90
     initially
    0.89
     instrumental
    0.89
     conceived
    0.88
    Act Density 0.411%

    No Known Activations