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

    Neuronpedia

    INDEX
    Explanations

    words related to hierarchy or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "top" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    signed
    -0.61
     @@
    -0.59
    gm
    -0.58
    ouri
    -0.56
    edIn
    -0.54
    ventions
    -0.54
    inea
    -0.52
    greg
    -0.52
    gerald
    -0.52
    rw
    -0.52
    POSITIVE LOGITS
    most
    1.08
     level
    0.91
     tier
    0.88
     thereof
    0.86
     of
    0.85
     tiers
    0.85
     edge
    0.84
     levels
    0.80
     shelf
    0.78
    mast
    0.78
    Act Density 0.047%

    No Known Activations