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

    Neuronpedia

    INDEX
    Explanations

    names or terms containing the word "kar"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kar" and related variations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UPS
    -0.65
     equals
    -0.63
     Doc
    -0.61
     normal
    -0.60
     certs
    -0.60
     fig
    -0.60
     suck
    -0.59
     Newfoundland
    -0.58
     ends
    -0.58
     MLS
    -0.58
    POSITIVE LOGITS
    kar
    4.61
    kat
    1.53
    kas
    1.51
    Kar
    1.47
    arov
    1.36
    kan
    1.36
    ka
    1.30
    krit
    1.26
    kh
    1.25
    kaya
    1.22
    Act Density 0.008%

    No Known Activations