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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "was" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zed
    -0.16
    gate
    -0.16
     Goose
    -0.14
     via
    -0.14
    ander
    -0.14
    andro
    -0.14
     Sullivan
    -0.14
    ÐĤ
    -0.14
     virgin
    -0.14
     holy
    -0.14
    POSITIVE LOGITS
    .AutoSizeMode
    0.19
    strup
    0.17
    eyse
    0.15
    /is
    0.15
    rut
    0.15
    ettel
    0.15
    átek
    0.15
    kyt
    0.14
    ÑĮв
    0.14
    745
    0.13
    Act Density 0.054%

    No Known Activations