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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ëħĦëıĦë³Ħ
    -0.17
    orate
    -0.15
    piration
    -0.14
    زÛĮ
    -0.14
    pollo
    -0.14
    è¼Ķ
    -0.14
    acle
    -0.14
    peed
    -0.13
    езÑĥлÑĮÑĤ
    -0.13
    aybe
    -0.13
    POSITIVE LOGITS
     effectively
    0.18
     evaluated
    0.18
     evaluates
    0.17
     íıīê°Ģ
    0.17
     evaluation
    0.17
     evaluate
    0.16
     Rubin
    0.16
     evaluating
    0.16
     Evalu
    0.16
     evaluations
    0.15
    Act Density 0.037%

    No Known Activations