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

    Neuronpedia

    INDEX
    Explanations

    instances of unique identifiers or markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pan
    -0.65
     “
    -0.64
     Finney
    -0.64
    es
    -0.61
     Zan
    -0.60
     Kre
    -0.60
    a
    -0.60
     Mu
    -0.60
    gew
    -0.59
     ‘
    -0.58
    POSITIVE LOGITS
    PerformLayout
    1.47
    ."</
    1.42
     ***!
    1.35
    InjectAttribute
    1.33
     CreateTagHelper
    1.33
     nakalista
    1.27
    ]")]
    1.23
    GEBURTSDATUM
    1.19
    %</
    1.14
    </caption>
    1.12
    Act Density 0.001%

    No Known Activations