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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols used in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    El
    -0.43
    ('*',
    -0.41
     El
    -0.41
    3
    -0.40
    B
    -0.39
     tali
    -0.38
    od
    -0.38
    4
    -0.38
    é
    -0.38
    H
    -0.37
    POSITIVE LOGITS
    PreferredItem
    1.16
    ########.
    1.08
    AndEndTag
    0.92
    GraphicsUnit
    0.85
    ValueStyle
    0.84
    +#+
    0.84
    исленность
    0.82
     surla
    0.81
    +#+#
    0.80
    EDEFAULT
    0.80
    Act Density 0.411%

    No Known Activations