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

    Neuronpedia

    INDEX
    Explanations

    the adverb "ever."

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

    ever since

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rull
    -0.45
     Brunch
    -0.45
     Kakashi
    -0.44
     Fielding
    -0.44
     Tia
    -0.43
    Salsa
    -0.43
    ILD
    -0.43
     Peanuts
    -0.43
     munic
    -0.43
    shampoo
    -0.43
    POSITIVE LOGITS
     ever
    1.09
     Ever
    1.00
     EVER
    0.97
    Ever
    0.91
    ever
    0.80
    EVER
    0.68
     Everett
    0.63
     jemals
    0.61
    łaszcza
    0.60
     enää
    0.57
    Act Density 0.008%

    No Known Activations