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

    Neuronpedia

    INDEX
    Explanations

    references to viral internet trends or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    processors
    -0.15
    707
    -0.15
    .toJSON
    -0.14
    etro
    -0.14
    roz
    -0.13
     å¤ı
    -0.13
    ÏĦαÏĥη
    -0.13
    uros
    -0.13
    BackingField
    -0.13
    etros
    -0.13
    POSITIVE LOGITS
     pr
    0.51
     practical
    0.44
     Practical
    0.40
     prank
    0.40
     Pr
    0.34
    pr
    0.33
    (pr
    0.29
    -pr
    0.28
    .pr
    0.27
    /pr
    0.27
    Act Density 0.081%

    No Known Activations