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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ìī
    -0.15
    ัà¹Ī
    -0.15
    prox
    -0.14
    ntl
    -0.14
    omo
    -0.14
    mlin
    -0.14
    ucch
    -0.14
     Karlov
    -0.13
    å¼ĥ
    -0.13
    uron
    -0.13
    POSITIVE LOGITS
     示
    0.16
    اÙģر
    0.15
    secure
    0.15
    mania
    0.15
    ÙĨاÙĨ
    0.15
    worth
    0.14
    illy
    0.14
    uner
    0.14
    brand
    0.14
    reds
    0.14
    Act Density 0.068%

    No Known Activations