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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and brackets in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    2
    -0.64
    -
    -0.56
    5
    -0.54
     
    -0.54
    3
    -0.54
    1
    -0.52
    9
    -0.51
    í
    -0.49
    <i>
    -0.48
     her
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    1.19
    帖最后由
    1.13
     AssemblyCulture
    1.05
    endphp
    1.04
    ,:),
    0.99
     feroit
    0.98
     plufieurs
    0.97
    Hentet
    0.97
    ]")]
    0.96
     ainfi
    0.95
    Act Density 0.474%

    No Known Activations