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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "though" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mel
    -0.15
     tháºŃm
    -0.14
    wor
    -0.14
    apolis
    -0.14
    PEnd
    -0.13
    طاÙĦ
    -0.13
    ropol
    -0.13
    utin
    -0.13
    akter
    -0.13
    δια
    -0.13
    POSITIVE LOGITS
     we
    0.21
     they
    0.20
     there
    0.20
     it
    0.18
    there
    0.14
    té
    0.14
     he
    0.14
    821
    0.14
    they
    0.13
     you
    0.13
    Act Density 0.091%

    No Known Activations