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

    Neuronpedia

    INDEX
    Explanations

    references to individual experiences and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orda
    -0.17
    antium
    -0.16
    atti
    -0.15
    lech
    -0.14
    Interop
    -0.14
     Mata
    -0.14
    inant
    -0.14
    flix
    -0.14
    landa
    -0.14
    oll
    -0.13
    POSITIVE LOGITS
     so
    0.18
    amak
    0.17
    GTK
    0.16
    uddle
    0.15
    gan
    0.15
     tolik
    0.15
     tanto
    0.15
    anto
    0.14
     tão
    0.14
    428
    0.14
    Act Density 0.140%

    No Known Activations