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

    Neuronpedia

    INDEX
    Explanations

    instructions or guidelines for taking specific actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SizePolicy
    -0.14
    sz
    -0.14
     Cic
    -0.13
    ctal
    -0.12
    DECL
    -0.12
    kara
    -0.12
    олод
    -0.12
    laps
    -0.12
    FromBody
    -0.12
    IDDLE
    -0.12
    POSITIVE LOGITS
    illac
    0.13
    adil
    0.13
     Quotes
    0.13
     fucking
    0.13
    oval
    0.13
    ipa
    0.13
    éĽ
    0.13
    е
    0.13
    ãng
    0.12
    oppable
    0.12
    Act Density 2.847%

    No Known Activations