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

    Neuronpedia

    INDEX
    Explanations

    the verb "is" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Word "is" followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    is that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.69
    expandindo
    -0.67
     themſelves
    -0.61
     favourably
    -0.59
     feroit
    -0.58
    autres
    -0.57
     Phoen
    -0.57
    AutoField
    -0.57
    SceneManagement
    -0.57
    protoimpl
    -0.57
    POSITIVE LOGITS
     the
    0.87
     simply
    0.86
     twofold
    0.85
    在于
    0.79
     simple
    0.78
     probably
    0.72
     actually
    0.70
     an
    0.68
     a
    0.66
    ########.
    0.66
    Act Density 0.244%

    No Known Activations