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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "and" in various contexts

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

    the word "and"

    np_acts-logits-general · gemini-2.0-flash

    auxiliary verbs after 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hinting
    -0.50
     signifying
    -0.47
     snowing
    -0.46
    allowing
    -0.46
     culminating
    -0.45
     interminable
    -0.44
    etc
    -0.43
     affecting
    -0.43
     provocando
    -0.43
     denoting
    -0.43
    POSITIVE LOGITS
     has
    1.17
     have
    1.03
     had
    0.95
     cannot
    0.95
     can
    0.94
     are
    0.94
     would
    0.91
     will
    0.91
     enjoys
    0.89
     is
    0.87
    Act Density 0.577%

    No Known Activations