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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific character or sign, likely the letter "L"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psychiat
    -0.80
     disadvant
    -0.79
     manif
    -0.79
     thous
    -0.78
     ende
    -0.78
     secretaries
    -0.77
     flourishing
    -0.76
     territ
    -0.76
     incorpor
    -0.76
     masse
    -0.75
    POSITIVE LOGITS
    ï¸ı
    0.91
    °
    0.90
    é¾į
    0.82
     âĢº
    0.80
    ef
    0.79
    º
    0.78
    Correction
    0.77
     Edited
    0.77
    STEM
    0.76
    Steam
    0.76
    Act Density 0.060%

    No Known Activations