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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or disbelief

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

    Follows negations or expressions of uncertainty

    np_acts-logits-general · gemini-2.0-flash

    not surprising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.89
     Theſe
    -0.85
     Reſ
    -0.84
     themſelves
    -0.83
     purpoſe
    -0.79
     ſche
    -0.77
     pleaſure
    -0.77
     himſelf
    -0.77
    UnknownFields
    -0.75
     ſeveral
    -0.75
    POSITIVE LOGITS
     wonder
    2.01
    wonder
    1.55
     Wonder
    1.42
    Wonder
    1.27
     wonders
    1.27
     WONDER
    1.23
    难怪
    1.12
     surprise
    1.09
     wondered
    1.02
     wondering
    0.98
    Act Density 0.120%

    No Known Activations