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

    Neuronpedia

    INDEX
    Explanations

    quotes and statements that emphasize critical evaluation and the questioning of authority or information sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .FontStyle
    -0.16
    senal
    -0.15
    $LANG
    -0.15
    .CustomButton
    -0.15
    IGO
    -0.15
    $MESS
    -0.14
    .scalablytyped
    -0.14
    VERTISEMENT
    -0.14
    ÑħодиÑĤÑĮ
    -0.14
    (LP
    -0.13
    POSITIVE LOGITS
     [
    0.27
    â
    0.18
    0.17
     (
    0.17
    0.16
     .
    0.16
    ene
    0.16
    ..
    0.16
    irt
    0.15
     often
    0.15
    Act Density 0.177%

    No Known Activations