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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or topics in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pfalz
    -1.02
     Culver
    -0.83
     “
    -0.83
    ません
    -0.78
    Topology
    -0.69
     McMillan
    -0.69
    UTO
    -0.68
     Vill
    -0.68
    ”
    -0.68
    “
    -0.67
    POSITIVE LOGITS
    {~
    1.39
     Gaud
    0.92
    --}}
    0.90
     useCallback
    0.85
    ViewInit
    0.84
    mallows
    0.84
    namese
    0.84
    wisata
    0.83
    "}")
    0.83
     Sampler
    0.82
    Act Density 0.219%

    No Known Activations