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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and related notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .vm
    -0.16
    ker
    -0.15
    KER
    -0.15
    elig
    -0.14
    ilig
    -0.14
    ied
    -0.14
    vert
    -0.14
    #Region
    -0.14
     Benchmark
    -0.14
    umbed
    -0.14
    POSITIVE LOGITS
     %#
    0.16
     Tonight
    0.16
    ritz
    0.15
    eful
    0.15
    éĻĦ
    0.14
    occ
    0.14
    oods
    0.14
    arel
    0.14
    asher
    0.14
    ood
    0.14
    Act Density 0.007%

    No Known Activations