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

    Neuronpedia

    INDEX
    Explanations

    references to libraries in programming or software contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ません
    -0.81
     Culver
    -0.77
     Pfalz
    -0.76
    Def
    -0.70
    Topology
    -0.69
    stdlib
    -0.69
     “
    -0.69
    POSS
    -0.69
    baya
    -0.68
    Vill
    -0.67
    POSITIVE LOGITS
    {~
    1.66
    wisata
    0.94
    --}}
    0.91
     Gaud
    0.85
    mallows
    0.84
     Sampler
    0.82
    ViewInit
    0.81
    úgó
    0.80
     BorderSide
    0.80
    quelles
    0.77
    Act Density 0.111%

    No Known Activations