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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters that are uncommon or not typically found in regular text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols typically found in non-English text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itch
    -0.73
     Gemini
    -0.72
    raints
    -0.71
    utterstock
    -0.67
     viability
    -0.67
    ukong
    -0.66
     inertia
    -0.66
    etsk
    -0.65
     Clarks
    -0.65
     tentacles
    -0.64
    POSITIVE LOGITS
    ña
    1.06
    ñ
    1.01
    ÃĽ
    0.99
    ï¸ı
    0.91
    lean
    0.91
    ļ
    0.87
    kay
    0.87
    ¹
    0.86
    µ
    0.86
    rug
    0.85
    Act Density 0.029%

    No Known Activations