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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "say" and its variations

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

    introduce hypothetical examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Toole
    -0.59
    ulco
    -0.52
     Tivoli
    -0.51
    mera
    -0.50
     BOC
    -0.50
     Elmo
    -0.50
    uram
    -0.50
    ubo
    -0.50
     Vesta
    -0.50
    WC
    -0.49
    POSITIVE LOGITS
    Say
    2.17
     Say
    2.14
    say
    1.82
    SAY
    1.67
     SAY
    1.66
     say
    1.43
     Says
    1.14
    Says
    1.09
    says
    1.03
     SAYS
    1.00
    Act Density 0.005%

    No Known Activations