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

    Neuronpedia

    INDEX
    Explanations

    references to critical reviews or assessments of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æģ¯
    -0.14
    endi
    -0.14
    égor
    -0.14
    andas
    -0.14
    .tm
    -0.14
    émon
    -0.14
    <?,
    -0.14
    RetVal
    -0.14
    paque
    -0.13
    >NN
    -0.13
    POSITIVE LOGITS
     Ellen
    0.15
     marginal
    0.14
    -->
    0.14
    ajan
    0.13
    sak
    0.13
    ous
    0.13
    iator
    0.13
    ilder
    0.13
     revolution
    0.13
    erval
    0.13
    Act Density 0.005%

    No Known Activations