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

    Neuronpedia

    INDEX
    Explanations

    phrases related to certainty and the limitations of guarantees

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

    followed by adverbs of degree

    np_acts-logits-general · gemini-2.0-flash

    completely stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.55
     immerhin
    -0.53
    Referències
    -0.47
    Varint
    -0.46
    Constru
    -0.45
    reten
    -0.43
     хоть
    -0.42
     Quince
    -0.42
    HTH
    -0.42
     Constru
    -0.42
    POSITIVE LOGITS
     completely
    1.10
     entirely
    0.98
     exclusively
    0.98
    completely
    0.95
     solely
    0.95
     fully
    0.93
     totally
    0.92
     perfect
    0.91
     Completely
    0.86
     perfectly
    0.84
    Act Density 0.537%

    No Known Activations