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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific sentence structures

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

    Follows an introductory word or phrase

    np_acts-logits-general · gemini-2.0-flash

    introduction sections, especially scientific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qrstuvwxyz
    -0.61
    也可
    -0.59
    Alternatively
    -0.58
     Otherwise
    -0.57
     Ferner
    -0.57
    也可以
    -0.55
     altrimenti
    -0.55
     Alternatively
    -0.55
     OTHERWISE
    -0.54
    calipsis
    -0.54
    POSITIVE LOGITS
     even
    0.87
     countless
    0.85
    Bahkan
    0.84
     Besonders
    0.79
    中でも
    0.77
    even
    0.76
     Bahkan
    0.76
    就连
    0.75
     sogar
    0.74
    无论是
    0.71
    Act Density 0.377%

    No Known Activations