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

    Neuronpedia

    INDEX
    Explanations

    instances and variations of the word "ever."

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

    "Ever" followed by a verb or adjective

    np_acts-logits-general · gemini-2.0-flash

    ever since

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.98
     altijd
    -0.82
     always
    -0.80
     siempre
    -0.77
    setVerticalGroup
    -0.77
    Always
    -0.75
     الحره
    -0.75
     всегда
    -0.73
     Always
    -0.69
    always
    -0.69
    POSITIVE LOGITS
    greens
    0.95
    lasting
    0.82
    glades
    0.78
     wondered
    0.75
    last
    0.65
     increasing
    0.62
    present
    0.62
    changing
    0.61
    thing
    0.61
    LAST
    0.59
    Act Density 0.030%

    No Known Activations