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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols used in code or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fieldNum
    -0.54
    儀
    -0.51
     Kec
    -0.48
    agic
    -0.48
     Magic
    -0.47
     mond
    -0.47
    vní
    -0.47
    Berg
    -0.46
    一二
    -0.45
     Morgen
    -0.45
    POSITIVE LOGITS
    =\
    1.44
    }=\
    1.10
    )=\
    1.07
     $=\
    1.01
     =\
    1.01
    ))=\
    0.98
    :=\
    0.94
    ]=\
    0.94
    |=\
    0.93
    \}=\
    0.92
    Act Density 0.055%

    No Known Activations