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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of authors or contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oola
    -0.17
    çĽĺ
    -0.17
    ibri
    -0.16
    缤
    -0.16
    loid
    -0.16
    (æľĪ
    -0.16
    actic
    -0.15
    oyal
    -0.15
    quent
    -0.15
    cade
    -0.15
    POSITIVE LOGITS
    cer
    0.17
     pret
    0.15
    zl
    0.14
    obra
    0.14
    pret
    0.14
     Trails
    0.14
    ment
    0.14
    izo
    0.14
    ested
    0.14
     Erl
    0.14
    Act Density 0.093%

    No Known Activations