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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Incontri
    -0.18
    herits
    -0.16
    _Tis
    -0.15
    á»įt
    -0.15
    uridad
    -0.15
    Å¡i
    -0.14
     æij
    -0.14
    alaxy
    -0.14
    regunta
    -0.14
    yms
    -0.14
    POSITIVE LOGITS
     Claud
    0.14
    mit
    0.14
    pliers
    0.14
     Bid
    0.14
    ilit
    0.13
    anel
    0.13
    hat
    0.13
    ëĵĿ
    0.13
    ato
    0.13
     bench
    0.13
    Act Density 0.078%

    No Known Activations