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

    Neuronpedia

    INDEX
    Explanations

    instances of refusals or denials in legal contexts

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

    after an event or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     irre
    -0.31
     cloche
    -0.31
     perform
    -0.30
     aero
    -0.30
    istock
    -0.29
     nepal
    -0.29
     prop
    -0.29
     sense
    -0.28
     aerop
    -0.28
    Bu
    -0.28
    POSITIVE LOGITS
     utafitiHapana
    0.84
    SequentialGroup
    0.72
    Ծանոթ
    0.68
     <<<<<<<<<<<<<<
    0.62
    Билгалдахарш
    0.62
    tagHelperRunner
    0.60
    Personendaten
    0.57
    Jîn
    0.57
    featureID
    0.56
     ProtoMessage
    0.56
    Act Density 0.269%

    No Known Activations