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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal indicators or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udd
    -0.16
    ruc
    -0.16
    FK
    -0.15
    iner
    -0.15
    olo
    -0.15
    uddy
    -0.15
    frei
    -0.14
    otten
    -0.14
    rie
    -0.14
    ombie
    -0.13
    POSITIVE LOGITS
    ervo
    0.16
     NDEBUG
    0.15
    antasy
    0.14
    ãĤ¤ãĥī
    0.14
    SearchTree
    0.14
    ICC
    0.14
    nameof
    0.14
    erox
    0.13
    DEX
    0.13
    aspers
    0.13
    Act Density 0.017%

    No Known Activations