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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases related to rankings or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azon
    -0.16
    олж
    -0.14
    él
    -0.14
     crud
    -0.13
    çµĮ
    -0.13
    anno
    -0.13
    OND
    -0.13
    ä¹Ĺ
    -0.13
    culus
    -0.13
     blat
    -0.13
    POSITIVE LOGITS
     runner
    0.37
     behind
    0.36
     close
    0.34
     closely
    0.33
     runners
    0.32
     distant
    0.32
     second
    0.30
     followed
    0.29
    close
    0.29
    Close
    0.28
    Act Density 0.109%

    No Known Activations