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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating strong affirmative sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .getvalue
    -0.15
    iversit
    -0.14
    version
    -0.14
    irk
    -0.14
    istani
    -0.14
    anim
    -0.14
    .chapter
    -0.14
    HK
    -0.13
     First
    -0.13
    ital
    -0.13
    POSITIVE LOGITS
    lei
    0.17
    (er
    0.15
    yyyy
    0.15
    /avatar
    0.14
    createForm
    0.14
    .ly
    0.13
    lake
    0.13
     Slee
    0.13
    yy
    0.13
    ActionButton
    0.13
    Act Density 0.073%

    No Known Activations