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

    Neuronpedia

    INDEX
    Explanations

    biographical information about individuals

    oai_token-act-pair · gpt-3.5-turbo

    identifying notable individuals' professions and their historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     takeaway
    -0.77
     rollout
    -0.77
     feedback
    -0.71
     baseline
    -0.68
    hazard
    -0.67
     responders
    -0.67
     Kinect
    -0.67
     Lavrov
    -0.66
     sidebar
    -0.66
     icing
    -0.65
    POSITIVE LOGITS
     youngest
    0.91
     eldest
    0.87
    ometown
    0.85
     Literary
    0.80
     granddaughter
    0.76
    Synopsis
    0.76
    Born
    0.76
     Originally
    0.75
     Born
    0.74
     born
    0.73
    Act Density 0.251%

    No Known Activations