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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" and related conjunctions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¾į
    -0.17
    rika
    -0.16
     addCriterion
    -0.15
    imu
    -0.15
    ä½
    -0.14
    ieux
    -0.14
    iron
    -0.13
    оги
    -0.13
    ikan
    -0.13
    ĶåĽŀ
    -0.13
    POSITIVE LOGITS
     its
    0.24
    its
    0.20
     Its
    0.18
    Its
    0.18
    ITS
    0.15
    ãģĿãģ®
    0.14
    thon
    0.14
     anc
    0.14
    global
    0.14
    umont
    0.14
    Act Density 0.221%

    No Known Activations