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

    Neuronpedia

    INDEX
    Explanations

    technical details related to parameters and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -1.01
     виправивши
    -0.85
    providedIn
    -0.76
    IntoConstraints
    -0.72
     Theſe
    -0.69
     المعيارى
    -0.68
     betweenstory
    -0.67
    expandindo
    -0.67
     CJK
    -0.67
    extAlignment
    -0.67
    POSITIVE LOGITS
     then
    0.62
     or
    0.61
    :
    0.54
    则
    0.50
     use
    0.50
     simply
    0.48
    則
    0.48
    (
    0.46
     else
    0.45
     generally
    0.45
    Act Density 0.587%

    No Known Activations