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

    Neuronpedia

    INDEX
    Explanations

    Māori or Polynesian words

    oai_token-act-pair · gpt-3.5-turbo

    repeated syllables or phonetic patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.92
    PORT
    -0.87
    Topics
    -0.77
    lings
    -0.76
    sets
    -0.76
    Product
    -0.75
    hetti
    -0.74
    tone
    -0.73
    wig
    -0.72
    Pope
    -0.72
    POSITIVE LOGITS
    jo
    0.86
     sher
    0.83
     ba
    0.77
    kered
    0.77
     weave
    0.76
    estro
    0.76
    ç
    0.76
     tha
    0.75
    ilt
    0.74
     la
    0.74
    Act Density 0.049%

    No Known Activations