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

    Neuronpedia

    INDEX
    Explanations

    words that indicate ownership, contributions, or conditions associated with financial and legal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frid
    -0.15
    VOICE
    -0.15
    eral
    -0.15
     nurse
    -0.14
    FFFFFFFF
    -0.14
    YNC
    -0.14
    Pros
    -0.14
    TRL
    -0.14
     Advantage
    -0.14
    Formats
    -0.13
    POSITIVE LOGITS
    exual
    0.15
    oser
    0.15
    .cam
    0.15
     Goose
    0.14
    èī
    0.14
    eds
    0.14
    laus
    0.14
    raž
    0.14
    DC
    0.14
    éd
    0.14
    Act Density 0.002%

    No Known Activations