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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "was" and related past tense forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.64
    iffion
    -0.51
    southeast
    -0.50
     Connectez
    -0.49
    AnchorStyles
    -0.48
    liferay
    -0.47
    enters
    -0.46
    ofern
    -0.45
     precisione
    -0.45
    outheast
    -0.45
    POSITIVE LOGITS
     were
    0.70
     WERE
    0.68
    were
    0.68
     Was
    0.67
     Were
    0.67
    Was
    0.63
    was
    0.63
     was
    0.60
     būtų
    0.60
    Were
    0.59
    Act Density 0.498%

    No Known Activations