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

    Neuronpedia

    INDEX
    Explanations

    various forms of lists, summaries, and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adverts
    -0.15
    \views
    -0.15
    ffa
    -0.15
    geois
    -0.15
     Manuals
    -0.15
    icket
    -0.15
    zing
    -0.14
    roje
    -0.14
    bbe
    -0.14
    ÙĪÙĨÙĬ
    -0.14
    POSITIVE LOGITS
     breakdown
    0.27
     sampling
    0.25
     rundown
    0.24
     run
    0.22
    sampling
    0.21
     running
    0.21
     look
    0.21
     quick
    0.21
     list
    0.21
     bird
    0.20
    Act Density 0.190%

    No Known Activations