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

    Neuronpedia

    INDEX
    Explanations

    names of researchers and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enties
    -0.15
    erm
    -0.15
    ensi
    -0.15
    епÑĤи
    -0.14
    RoutingModule
    -0.14
    ocoa
    -0.14
     Hir
    -0.14
     kne
    -0.13
    amide
    -0.13
     pres
    -0.13
    POSITIVE LOGITS
    adia
    0.15
    RYPT
    0.15
    _serialize
    0.14
    acha
    0.14
     Benchmark
    0.14
     Äijô
    0.14
    æķ£
    0.14
    jj
    0.13
    adt
    0.13
    æĬµ
    0.13
    Act Density 0.283%

    No Known Activations