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

    Neuronpedia

    INDEX
    Explanations

    statements involving personal beliefs and opinions

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

    I think, I believe, possibly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.52
    -0.52
     houſe
    -0.47
     ſtand
    -0.47
    neſs
    -0.47
     Sénat
    -0.46
     ModelRenderer
    -0.46
     Houſe
    -0.45
    erçe
    -0.45
     purpoſe
    -0.44
    POSITIVE LOGITS
    rungsseite
    0.53
    ?)
    0.50
    ?).
    0.49
     probably
    0.47
    Probably
    0.46
    ](#
    0.45
     maybe
    0.45
     Probably
    0.45
     Pretty
    0.43
    (?)
    0.43
    Act Density 0.031%

    No Known Activations