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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditionality and necessary actions or requirements

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

    "Is" appearing in specific grammar structures

    np_acts-logits-general · gemini-2.0-flash

    is useful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eſ
    -0.86
     Monfieur
    -0.85
     Conſ
    -0.85
     purpoſe
    -0.84
     ſta
    -0.82
     Efq
    -0.80
     Majefty
    -0.80
     faſt
    -0.78
     ſtate
    -0.78
     raiſ
    -0.78
    POSITIVE LOGITS
     its
    1.62
    Its
    1.21
     Its
    1.17
    使其
    1.03
    其
    1.03
    its
    0.97
     it
    0.96
    对其
    0.86
    及其
    0.84
     their
    0.81
    Act Density 0.788%

    No Known Activations