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

    Neuronpedia

    INDEX
    Explanations

    references to characters in dialogues and interactions within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dimit
    -0.15
    illon
    -0.15
    ONO
    -0.14
    ono
    -0.14
    eron
    -0.14
    zier
    -0.14
    oral
    -0.13
    116
    -0.13
     Arg
    -0.13
    rait
    -0.13
    POSITIVE LOGITS
     Jones
    0.23
     Smith
    0.23
    Smith
    0.22
    Jones
    0.20
     Mary
    0.20
     smith
    0.20
     Doe
    0.18
     Johns
    0.18
     Frank
    0.18
     Brown
    0.17
    Act Density 0.169%

    No Known Activations