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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know" and its variants in various contexts

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

    "know" or its inflections

    np_acts-logits-general · gemini-2.0-flash

    know what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.63
    dhist
    -0.60
     Ambas
    -0.56
    qxd
    -0.55
    ábbi
    -0.54
     Tigre
    -0.52
    ichtig
    -0.52
     Dempsey
    -0.52
    Marcus
    -0.52
     Corbett
    -0.51
    POSITIVE LOGITS
    know
    1.32
    Know
    1.31
     Know
    1.30
     know
    1.27
    KNOW
    1.25
     knows
    1.24
     KNOW
    1.21
     Knows
    1.15
    knew
    1.11
    knows
    1.08
    Act Density 0.138%

    No Known Activations