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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate actions related to governance or public decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /INFO
    -0.17
    éĤ£äºĽ
    -0.17
    ipa
    -0.15
    occo
    -0.15
    好çļĦ
    -0.15
    ìłij
    -0.15
     ÙħØŃÙĦ
    -0.14
    niž
    -0.14
     detriment
    -0.13
     Contacts
    -0.13
    POSITIVE LOGITS
     formal
    0.21
     immediate
    0.21
     ÂŃ
    0.20
     direct
    0.20
     actual
    0.18
     nominal
    0.17
     initial
    0.17
     further
    0.17
     repeated
    0.17
     full
    0.16
    Act Density 0.303%

    No Known Activations