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

    Neuronpedia

    INDEX
    Explanations

    expressions related to social justice and inequality

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

    preceding "will," "do," or "does."

    np_acts-logits-general · gemini-2.0-flash

    subjects followed by do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.73
    __*/
    -0.68
    RegressionTest
    -0.64
    /$',
    -0.64
    <bos>
    -0.62
    rizona
    -0.61
    missible
    -0.58
    TargetException
    -0.58
    ensible
    -0.58
    IZONTAL
    -0.56
    POSITIVE LOGITS
     did
    2.08
     does
    1.89
     do
    1.72
    did
    1.69
    Did
    1.54
    does
    1.51
     Did
    1.48
    Does
    1.45
     Does
    1.42
     DID
    1.40
    Act Density 0.194%

    No Known Activations