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

    Neuronpedia

    INDEX
    Explanations

    frequent conjunctions and phrases that indicate relationships between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ade
    -0.16
    UNCH
    -0.14
    unch
    -0.14
    tr
    -0.14
    una
    -0.13
     æķ
    -0.13
    obj
    -0.13
    asil
    -0.13
    iana
    -0.13
    pon
    -0.13
    POSITIVE LOGITS
    ecycle
    0.16
    /***/
    0.15
    vanced
    0.15
    erson
    0.15
     zdrav
    0.15
    æĹıèĩªæ²»
    0.15
    .bootstrapcdn
    0.14
    sted
    0.14
    antz
    0.14
    รà¸ģ
    0.14
    Act Density 0.457%

    No Known Activations