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

    Neuronpedia

    INDEX
    Explanations

    instances of strong emphasis or importance in content, such as references to live streaming and significant topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.48
     Bed
    -0.46
    taman
    -0.44
     v
    -0.44
     She
    -0.44
    ules
    -0.44
     The
    -0.42
    springframework
    -0.42
     So
    -0.40
    deman
    -0.40
    POSITIVE LOGITS
     itſelf
    1.14
    ſelves
    1.09
     themſelves
    1.04
    AddTagHelper
    1.03
     Efq
    1.02
    ſelf
    1.02
     myſelf
    1.02
     himſelf
    0.99
     purpoſe
    0.98
     ſeveral
    0.98
    Act Density 0.013%

    No Known Activations