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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or bureaucratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exo
    -0.16
     partager
    -0.15
    à¥Ĥड
    -0.15
    opsis
    -0.14
    olia
    -0.14
     absl
    -0.14
    irut
    -0.14
    entin
    -0.14
     endregion
    -0.14
    _unused
    -0.14
    POSITIVE LOGITS
     wor
    0.19
     awkward
    0.18
    emb
    0.17
     uncomfortable
    0.17
     regret
    0.17
     problematic
    0.16
     parl
    0.16
     nerve
    0.15
     preca
    0.15
     combust
    0.15
    Act Density 0.023%

    No Known Activations