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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "finished" and its variations related to competition outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lingen
    -0.18
    rana
    -0.16
    _Ptr
    -0.16
    ective
    -0.15
    chw
    -0.15
     queryInterface
    -0.14
     Cons
    -0.14
    agna
    -0.14
    alty
    -0.14
    arak
    -0.14
    POSITIVE LOGITS
    enor
    0.17
    esser
    0.17
    omo
    0.15
    ranges
    0.15
     Bow
    0.15
    erin
    0.15
     bow
    0.14
     WHATSOEVER
    0.14
    umer
    0.14
    éģĵ
    0.14
    Act Density 0.014%

    No Known Activations