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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to place names, especially containing the term "Ches"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.80
    ENGTH
    -0.76
     Rw
    -0.70
    anguages
    -0.62
     bounds
    -0.62
    ially
    -0.61
    pport
    -0.61
     Slovenia
    -0.60
    iance
    -0.58
     Ronaldo
    -0.58
    POSITIVE LOGITS
    apeake
    1.63
    hire
    1.28
    nut
    1.03
    ney
    0.97
    creen
    0.88
    uits
    0.86
    romancer
    0.84
    erver
    0.84
    bury
    0.82
    uba
    0.81
    Act Density 0.020%

    No Known Activations