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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urm
    -0.17
    ipi
    -0.17
    _Impl
    -0.16
    anz
    -0.15
    ινε
    -0.15
    jax
    -0.15
    áj
    -0.14
    ipe
    -0.14
    ith
    -0.14
    InSection
    -0.14
    POSITIVE LOGITS
    erald
    0.17
    nard
    0.16
    iator
    0.15
    ENCY
    0.15
     Siz
    0.15
    ndern
    0.15
    amen
    0.14
     Gerard
    0.13
    ÙĬات
    0.13
    zsche
    0.13
    Act Density 0.059%

    No Known Activations