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

    Neuronpedia

    INDEX
    Explanations

    terms indicating authenticity or reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ones
    -0.19
    ansen
    -0.16
    onto
    -0.16
     Ones
    -0.16
    phere
    -0.14
    ngr
    -0.14
    nt
    -0.14
    herent
    -0.14
    DataProvider
    -0.14
    engkap
    -0.14
    POSITIVE LOGITS
    ingly
    0.23
    atively
    0.22
    edly
    0.22
    ively
    0.20
    ably
    0.19
    aneously
    0.19
    ely
    0.18
    /false
    0.18
    ily
    0.18
     contrast
    0.18
    Act Density 0.049%

    No Known Activations