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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific processes and methods, particularly in experimental contexts

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

    Passive voice after "were," "was," or "be"

    np_acts-logits-general · gemini-2.0-flash

    be + past participle verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.97
     poffible
    -0.94
     myſelf
    -0.89
     ſeveral
    -0.88
     perſon
    -0.88
     pleaſure
    -0.87
     ſche
    -0.84
     becauſe
    -0.84
     Monfieur
    -0.84
     ſaid
    -0.82
    POSITIVE LOGITS
    pexpr
    0.56
     slide
    0.54
     sun
    0.52
    ')):
    0.51
     Sun
    0.51
     run
    0.50
    "):
    0.49
     Gulf
    0.48
     Slide
    0.47
     den
    0.47
    Act Density 0.483%

    No Known Activations