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

    Neuronpedia

    INDEX
    Explanations

    terms and variations related to "norm" or "normalcy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idebar
    -0.16
    ernet
    -0.15
    iron
    -0.15
    nown
    -0.15
    ERN
    -0.15
    ernes
    -0.15
    bles
    -0.15
    ern
    -0.15
    502
    -0.15
     Clem
    -0.14
    POSITIVE LOGITS
    cy
    0.26
    ative
    0.23
    atively
    0.22
    anton
    0.20
    andy
    0.20
    angep
    0.18
    olle
    0.18
    izr
    0.16
    deaux
    0.16
    rig
    0.15
    Act Density 0.046%

    No Known Activations