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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "does."

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

    how does questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.81
    ſelves
    -0.79
     Houſe
    -0.79
     ſche
    -0.75
    ſelf
    -0.73
    存于互联网档案馆
    -0.73
     myſelf
    -0.69
    EDEFAULT
    -0.69
    parsedMessage
    -0.69
     queſta
    -0.68
    POSITIVE LOGITS
    Does
    1.10
     Does
    1.05
    does
    0.98
     does
    0.93
    DOES
    0.79
     DOES
    0.73
    s
    0.47
    es
    0.46
     Has
    0.45
     
    0.45
    Act Density 0.008%

    No Known Activations