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

    Neuronpedia

    INDEX
    Explanations

    numerical data and metrics related to performance, duration, and estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lec
    -0.18
    oot
    -0.16
     Sister
    -0.14
    gard
    -0.14
    brid
    -0.13
     her
    -0.13
     Haskell
    -0.13
    ein
    -0.13
    eg
    -0.13
     gard
    -0.13
    POSITIVE LOGITS
     moden
    0.16
    quier
    0.15
    erne
    0.15
    agara
    0.15
    entai
    0.14
    áºŃt
    0.14
     konkrét
    0.14
    úde
    0.14
    Convention
    0.14
    akter
    0.14
    Act Density 0.151%

    No Known Activations