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

    Neuronpedia

    INDEX
    Explanations

    questions and statements expressing confusion or concern about reasons behind actions or situations

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

    "Why" and subsequent words

    np_acts-logits-general · gemini-2.0-flash

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.71
    +#+#
    -0.70
    \{\\
    -0.70
     gynhyrchwyd
    -0.68
     propOrder
    -0.65
    StoryboardSegue
    -0.65
     autorytatywna
    -0.65
    __":
    -0.63
    __':
    -0.63
     contextLoads
    -0.62
    POSITIVE LOGITS
    竟
    0.43
    为何
    0.41
     why
    0.40
     kenapa
    0.39
    為何
    0.39
    竟然
    0.38
     warum
    0.38
    Why
    0.36
     suddenly
    0.36
    为什么
    0.35
    Act Density 0.307%

    No Known Activations