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

    Neuronpedia

    INDEX
    Explanations

    numerical data representations

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.75
     autorytatywna
    -0.73
    Personensuche
    -0.69
    oa̍t
    -0.68
    complexContent
    -0.68
    Autoritní
    -0.65
    tvguidetime
    -0.65
    ArrowToggle
    -0.65
    -------
    -0.64
    __":
    -0.64
    POSITIVE LOGITS
     his
    0.35
     also
    0.32
     combine
    0.32
     lab
    0.32
     Kal
    0.30
     Hil
    0.29
     GU
    0.29
     flavour
    0.28
     ésta
    0.27
    擅长
    0.27
    Act Density 0.013%

    No Known Activations