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

    Neuronpedia

    INDEX
    Explanations

    references to prior studies and their results within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.91
    ंदीखरीदारी
    -0.83
    FormTagHelper
    -0.82
    Jereo
    -0.81
    CloseOperation
    -0.80
     فريبيس
    -0.77
    IntoConstraints
    -0.76
    -0.75
    principalColumn
    -0.73
    GEBURTSDATUM
    -0.70
    POSITIVE LOGITS
     reported
    0.71
     previously
    0.69
     previous
    0.54
     published
    0.53
    previously
    0.52
     suggested
    0.51
     authors
    0.50
    reported
    0.50
     proposed
    0.50
     cited
    0.49
    Act Density 2.399%

    No Known Activations