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

    Neuronpedia

    INDEX
    Explanations

    terms related to normalcy or standard measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dreyfus
    -0.77
    anek
    -0.68
    💲
    -0.68
    Dund
    -0.68
    entyfik
    -0.67
    ktı
    -0.65
    annia
    -0.65
     laissé
    -0.63
    Conte
    -0.63
     sphinct
    -0.63
    POSITIVE LOGITS
     NORMAL
    2.08
     Normal
    2.06
     normal
    2.05
    Normal
    2.01
    normal
    2.01
    NORMAL
    1.93
     normals
    1.89
     normale
    1.66
     normales
    1.59
    ORMAL
    1.57
    Act Density 0.074%

    No Known Activations