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

    Neuronpedia

    INDEX
    Explanations

    transitional conjunctions and phrases indicating contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     же
    -0.15
    èĥŀ
    -0.14
    axon
    -0.13
     Lomb
    -0.13
    ÃŃnÄĽ
    -0.13
    ossal
    -0.13
    702
    -0.13
    esinin
    -0.13
    geois
    -0.13
    vester
    -0.12
    POSITIVE LOGITS
    AIM
    0.16
    DATES
    0.15
    ilde
    0.15
    ìĦľëĬĶ
    0.14
    aim
    0.14
    atan
    0.14
    çĩ
    0.13
    amy
    0.13
    öz
    0.13
    sn
    0.13
    Act Density 0.083%

    No Known Activations