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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic characters mixed with Latin characters

    oai_token-act-pair · gpt-3.5-turbo

    patterns of special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.72
     Dresden
    -0.71
    wagen
    -0.70
     Rescue
    -0.68
     Bentley
    -0.67
    istries
    -0.66
     Chapman
    -0.66
     Dane
    -0.64
     Hendricks
    -0.63
     Dres
    -0.63
    POSITIVE LOGITS
     denotes
    0.75
    ateful
    0.73
    cffffcc
    0.71
    ream
    0.68
     }}
    0.66
     signifies
    0.63
    auri
    0.63
    orah
    0.62
    amount
    0.62
     denote
    0.61
    Act Density 0.280%

    No Known Activations