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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    728
    -0.16
     Saul
    -0.15
    lected
    -0.15
    ands
    -0.15
    ppers
    -0.15
    pper
    -0.14
     Gross
    -0.14
    eed
    -0.14
     Peach
    -0.14
    ective
    -0.14
    POSITIVE LOGITS
    akit
    0.17
    виÑĤ
    0.14
     Ngh
    0.14
    utan
    0.14
     Cousins
    0.14
    roleum
    0.14
     Nim
    0.13
    ITIONAL
    0.13
    chwitz
    0.13
    íĹĪ
    0.13
    Act Density 0.018%

    No Known Activations