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

    Neuronpedia

    INDEX
    Explanations

    terms related to government levels and jurisdiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    visor
    -0.17
    orre
    -0.15
    olic
    -0.14
    ITH
    -0.14
    anel
    -0.14
     Counties
    -0.14
    coni
    -0.14
     Telescope
    -0.14
     fak
    -0.13
     Ville
    -0.13
    POSITIVE LOGITS
    -wide
    0.34
    /local
    0.31
    -level
    0.30
    wide
    0.28
    -local
    0.24
    -Level
    0.24
     wide
    0.24
    Wide
    0.23
     level
    0.22
    /global
    0.22
    Act Density 0.118%

    No Known Activations