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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to coding and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUADS
    -0.46
    awtextra
    -0.46
     للمعارف
    -0.40
    xt
    -0.40
     clip
    -0.39
    archiviato
    -0.38
     bug
    -0.38
    誇
    -0.37
     TestBed
    -0.37
     kit
    -0.37
    POSITIVE LOGITS
    Datuak
    0.49
     pinulongan
    0.48
     règne
    0.48
    IsContent
    0.47
     aceptas
    0.45
     <>",
    0.45
     enamorado
    0.43
     valiente
    0.42
    RegressionTest
    0.42
     виправивши
    0.42
    Act Density 1.823%

    No Known Activations