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

    Neuronpedia

    INDEX
    Explanations

    instances of surprise or wonder related to events or actions

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

    wonder why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suspensão
    -0.46
    SharedCtor
    -0.45
    bkz
    -0.40
    :+:
    -0.40
    getMenuInflater
    -0.39
     typelib
    -0.39
    \{\\
    -0.38
    المكان
    -0.37
     sequência
    -0.36
     ит
    -0.34
    POSITIVE LOGITS
    难怪
    1.04
     wonder
    0.96
    wonder
    0.81
     why
    0.77
    why
    0.73
     WONDER
    0.71
    WHY
    0.68
    Why
    0.68
     Why
    0.68
    Neden
    0.68
    Act Density 0.004%

    No Known Activations