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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and references to organizational bodies or formal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARDS
    -0.17
    mere
    -0.16
    á»ĩn
    -0.15
    ControlItem
    -0.15
    ichi
    -0.15
    AINED
    -0.15
    hoe
    -0.14
    ĵåIJį
    -0.14
    зÑĭ
    -0.14
    ISED
    -0.14
    POSITIVE LOGITS
    -spacing
    0.16
    ör
    0.14
    æµ´
    0.14
    ahir
    0.14
    *Math
    0.14
    UY
    0.14
    uye
    0.14
    illage
    0.14
     Drake
    0.13
    agent
    0.13
    Act Density 0.025%

    No Known Activations