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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Elijah
    -0.47
    Ronald
    -0.47
    Kenneth
    -0.43
     muž
    -0.42
    Derek
    -0.42
    Trevor
    -0.41
    Anthony
    -0.41
    Charles
    -0.40
    Richard
    -0.40
    Robert
    -0.40
    POSITIVE LOGITS
     Ann
    0.84
     Anne
    0.78
     Maria
    0.78
     Sara
    0.78
     Mary
    0.77
     Anna
    0.77
     Laura
    0.75
     Sarah
    0.75
     Marie
    0.73
    Ann
    0.73
    Act Density 0.906%

    No Known Activations