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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of doubt or disbelief

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

    Followed by a question mark, comma, or exclamation point after "Why" or "No"

    np_acts-logits-general · gemini-2.0-flash

    why, no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.12
    couvrez
    -1.00
    ftagPool
    -0.99
    __()
    -0.97
     pinulongan
    -0.95
    KommentareTeilen
    -0.95
    ^(@)
    -0.95
     Efq
    -0.91
    Попис
    -0.91
     виправивши
    -0.91
    POSITIVE LOGITS
    '
    0.70
    g
    0.68
    ’
    0.64
    j
    0.61
    man
    0.60
    k
    0.60
    an
    0.59
    o
    0.59
    h
    0.59
    m
    0.59
    Act Density 0.273%

    No Known Activations