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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of specific locations or establishments

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneously
    -0.86
    linked
    -0.76
    udeau
    -0.75
    llor
    -0.73
    ubuntu
    -0.73
    Downloadha
    -0.73
    ilater
    -0.73
    ocument
    -0.71
    GBT
    -0.71
    icity
    -0.69
    POSITIVE LOGITS
     Revenge
    1.08
     Creek
    0.99
     Corner
    0.96
     Tavern
    0.95
     Own
    0.94
     Mansion
    0.93
     Tale
    0.92
     Syndrome
    0.92
     finest
    0.91
     Daughter
    0.91
    Act Density 0.126%

    No Known Activations