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

    Neuronpedia

    INDEX
    Explanations

    references to "normal" in various contexts, indicating standard or typical conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Riviera
    -0.70
    Deja
    -0.70
    anek
    -0.68
     Polonia
    -0.66
     Dreyfus
    -0.65
    vábbi
    -0.64
     Scripps
    -0.64
    annia
    -0.62
     Kishi
    -0.62
     Waugh
    -0.61
    POSITIVE LOGITS
    ORMAL
    1.14
     normals
    1.09
     Norma
    1.05
     Norm
    0.90
     NORMAL
    0.89
    normals
    0.87
    Normals
    0.87
     Normal
    0.84
    ormal
    0.82
     Norman
    0.82
    Act Density 0.063%

    No Known Activations