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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and encouragement in a communal context

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

    Punctuation followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    . followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.75
    MigrationBuilder
    -0.75
    CreateModel
    -0.75
    tonsoft
    -0.71
    ValueStyle
    -0.71
    RegistryLite
    -0.71
    HideFlags
    -0.71
    PMailer
    -0.70
    wpi
    -0.70
     ChromeDriver
    -0.69
    POSITIVE LOGITS
     Remember
    1.02
     Don
    0.99
     Happy
    0.98
     remember
    0.94
     Have
    0.92
    Happy
    0.89
    Remember
    0.89
     don
    0.87
     Enjoy
    0.82
    Don
    0.81
    Act Density 0.121%

    No Known Activations