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

    Neuronpedia

    INDEX
    Explanations

    the letter "k"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the letter 'k' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.85
     Revel
    -0.71
    enance
    -0.70
     Compass
    -0.67
     Remastered
    -0.67
    aign
    -0.64
    itial
    -0.64
     Heard
    -0.62
    OPE
    -0.61
    rentice
    -0.61
    POSITIVE LOGITS
     k
    3.17
     K
    1.75
     ke
    1.73
     ka
    1.70
     ko
    1.70
    k
    1.63
    K
    1.53
     kh
    1.52
     ak
    1.52
     kan
    1.37
    Act Density 0.016%

    No Known Activations