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

    Neuronpedia

    INDEX
    Explanations

    occurrences of reporting or referencing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emens
    -0.18
    lém
    -0.15
    unately
    -0.15
    -flat
    -0.14
     Accounts
    -0.14
    ozÃŃ
    -0.14
    人åı£
    -0.13
    eed
    -0.13
    akest
    -0.13
    260
    -0.13
    POSITIVE LOGITS
     according
    0.18
    "While
    0.16
    According
    0.16
     According
    0.16
    according
    0.15
    qu
    0.15
    bnb
    0.15
     Writes
    0.14
    ipay
    0.14
    олее
    0.14
    Act Density 0.078%

    No Known Activations