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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xbc
    -0.15
    arkan
    -0.14
    vik
    -0.14
    anie
    -0.13
     alike
    -0.13
     ilk
    -0.13
    olec
    -0.13
     aquarium
    -0.13
    _NOP
    -0.13
    olt
    -0.13
    POSITIVE LOGITS
     there
    0.28
    there
    0.21
     we
    0.17
     THERE
    0.17
    人们
    0.16
     everyone
    0.15
    717
    0.15
    tere
    0.15
    atar
    0.14
    we
    0.14
    Act Density 0.242%

    No Known Activations