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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "known."

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

    known as, to, for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Montagu
    -0.55
    pellier
    -0.51
     Fletcher
    -0.50
    parser
    -0.49
    Herzliche
    -0.49
    fenster
    -0.47
    iermark
    -0.47
    menü
    -0.46
     Sommers
    -0.45
    spider
    -0.45
    POSITIVE LOGITS
     Known
    1.31
    Known
    1.25
     known
    1.23
    KNOWN
    1.22
     KNOWN
    1.20
    known
    1.13
    Know
    1.02
     Know
    0.94
     Knew
    0.88
    Knows
    0.88
    Act Density 0.022%

    No Known Activations