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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases or questions

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

    questions starting with "does"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.80
    存于互联网档案馆
    -0.78
    iſchen
    -0.77
    enablog
    -0.73
     queſto
    -0.71
    iſche
    -0.70
    -0.68
    parsedMessage
    -0.68
    <pad>
    -0.67
    <unused3>
    -0.67
    POSITIVE LOGITS
    Does
    1.53
     Does
    1.48
    DOES
    1.08
    does
    1.05
     DOES
    0.89
     does
    0.77
    Is
    0.69
    Did
    0.65
     Did
    0.63
    Has
    0.60
    Act Density 0.012%

    No Known Activations