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

    Neuronpedia

    INDEX
    Explanations

    questionable assumptions and arguments in discussions

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

    questions ending in question marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.51
    WaitGroup
    -0.49
    ########.
    -0.48
    errHandler
    -0.46
     gärna
    -0.44
    EDEFAULT
    -0.43
    ftant
    -0.43
    WebServlet
    -0.43
    cademic
    -0.42
    ніципалі
    -0.41
    POSITIVE LOGITS
    ?
    1.05
    ?”
    0.93
    ؟
    0.89
    ?"
    0.86
    ?)
    0.85
    ?
    0.85
    ?(
    0.84
    ()?
    0.83
    ?).
    0.82
    ?),
    0.82
    Act Density 0.163%

    No Known Activations