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

    Neuronpedia

    INDEX
    Explanations

    items or paragraphs that contain clauses or phrases, particularly those involving criticism or societal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irling
    -0.17
    dit
    -0.15
    è¸
    -0.15
    igham
    -0.14
    ÙĥÙĬØ©
    -0.14
    orna
    -0.14
    atan
    -0.14
    ducted
    -0.14
    ulnerable
    -0.14
    loat
    -0.14
    POSITIVE LOGITS
    .sendStatus
    0.14
    Pros
    0.14
    ald
    0.14
    atel
    0.13
    abus
    0.13
     Hass
    0.13
     Joi
    0.13
     fort
    0.13
    .documentation
    0.13
    ress
    0.12
    Act Density 0.099%

    No Known Activations