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

    Neuronpedia

    INDEX
    Explanations

    the name "Kl" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Klump."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.67
     Civic
    -0.67
    Interstitial
    -0.65
     Regulatory
    -0.65
     mant
    -0.63
     Thumbnails
    -0.62
     plural
    -0.62
     squash
    -0.62
     FANTASY
    -0.62
     Chaser
    -0.61
    POSITIVE LOGITS
    assic
    1.36
    itsch
    1.33
    utz
    1.24
    oser
    1.17
    utch
    1.16
    oves
    1.12
    usk
    1.12
    osing
    1.10
    avier
    1.09
    ubb
    1.08
    Act Density 0.018%

    No Known Activations