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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting related to mathematical notation and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .appspot
    -0.16
    .ease
    -0.15
     DEALINGS
    -0.15
    dete
    -0.15
    LOBAL
    -0.14
    enso
    -0.14
    리ì¦Ī
    -0.14
    $MESS
    -0.13
    edik
    -0.13
    entials
    -0.13
    POSITIVE LOGITS
    asher
    0.16
    732
    0.15
    aktu
    0.15
     Wa
    0.14
    ekk
    0.14
    outu
    0.14
     Geh
    0.13
     micro
    0.13
    uggy
    0.13
     sub
    0.13
    Act Density 0.037%

    No Known Activations