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

    Neuronpedia

    INDEX
    Explanations

    words indicating recent alterations or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexType
    -0.91
    tagext
    -0.81
    withstanding
    -0.80
    culares
    -0.78
    EndContext
    -0.77
     Tomar
    -0.77
     Bakan
    -0.77
     Alden
    -0.76
    aneous
    -0.75
     Elbow
    -0.75
    POSITIVE LOGITS
     newly
    1.06
    Newly
    1.03
     Newly
    1.02
    newly
    0.94
    yarnpkg
    0.77
     freshly
    0.75
     recently
    0.73
     nowo
    0.70
     formerly
    0.70
    recently
    0.69
    Act Density 0.071%

    No Known Activations