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

    Neuronpedia

    INDEX
    Explanations

    the word "Zeppelin" with varying degrees of association

    oai_token-act-pair · gpt-3.5-turbo

    references to "Zeppelin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wear
    -0.73
    channelAvailability
    -0.70
    yrinth
    -0.70
    Interstitial
    -0.70
    ainers
    -0.68
     AVG
    -0.66
    DOWN
    -0.64
    姫
    -0.63
    ials
    -0.63
    ãģį
    -0.63
    POSITIVE LOGITS
    ppelin
    1.23
    lda
    1.08
    itsch
    1.02
    plin
    0.92
    pez
    0.90
    ppel
    0.88
     Ze
    0.86
    iger
    0.85
    ben
    0.85
    cks
    0.84
    Act Density 0.024%

    No Known Activations