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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know" and its variations, indicating a focus on knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mengel
    -0.65
     Efforts
    -0.64
     Gill
    -0.63
     Tos
    -0.61
    TEntity
    -0.61
    dhist
    -0.60
    qxd
    -0.60
    Pal
    -0.59
     Phelps
    -0.58
    ADF
    -0.58
    POSITIVE LOGITS
    know
    1.72
     know
    1.70
    Know
    1.70
     Know
    1.68
     knows
    1.68
    KNOW
    1.60
    knows
    1.58
     KNOW
    1.57
     Knows
    1.55
    knew
    1.48
    Act Density 0.123%

    No Known Activations