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

    Neuronpedia

    INDEX
    Explanations

    punctuation patterns and their context in sentences

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

    Text before a comma

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    -0.65
     ,
    -0.64
     -,
    -0.62
     jedoch
    -0.60
     welcher
    -0.59
     Также
    -0.55
     somit
    -0.54
     также
    -0.54
    ;',
    -0.53
     —,
    -0.53
    POSITIVE LOGITS
     dammit
    0.81
    WriteBarrier
    0.77
     lest
    0.77
     jedenfalls
    0.73
     pronto
    0.73
     certainly
    0.71
     almeno
    0.71
    certainly
    0.69
    ">//
    0.68
    GraphicsUnit
    0.67
    Act Density 0.357%

    No Known Activations