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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    programming and code-related terms and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ambro
    -0.70
     microphones
    -0.64
    20439
    -0.63
     mathemat
    -0.63
     acron
    -0.62
     Tao
    -0.61
     Freem
    -0.61
     jaw
    -0.61
     harmony
    -0.61
     monog
    -0.60
    POSITIVE LOGITS
     +=
    1.16
     =
    1.10
     !=
    1.05
     ->
    1.03
     ==
    1.03
     +
    1.00
     -=
    0.96
     ||
    0.96
    ->
    0.95
     &&
    0.95
    Act Density 0.105%

    No Known Activations