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

    Neuronpedia

    INDEX
    Explanations

    specific sequences and patterns in text that resemble code or data structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -1.09
    t
    -0.96
    i
    -0.88
    k
    -0.86
    u
    -0.85
    o
    -0.84
    ه
    -0.80
    an
    -0.80
    in
    -0.78
    d
    -0.75
    POSITIVE LOGITS
    +#+#
    1.06
    thâu
    0.90
     propOrder
    0.88
    ítmény
    0.88
     alimentaires
    0.85
     AssemblyCulture
    0.84
    Przypisy
    0.84
     ModelExpression
    0.84
    DoS
    0.83
    ]")]
    0.83
    Act Density 1.400%

    No Known Activations