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

    Neuronpedia

    INDEX
    Explanations

    numerical data, such as dates, quantities, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of end-of-text markers or punctuation indicating the end of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.82
     neighb
    -0.78
     predec
    -0.70
     destro
    -0.69
     behavi
    -0.67
    akespe
    -0.66
     administr
    -0.64
     infl
    -0.64
     undermin
    -0.64
     assum
    -0.61
    POSITIVE LOGITS
     Died
    0.77
     Introduction
    0.73
     Killed
    0.73
    09
    0.71
    2018
    0.71
    1945
    0.71
     Learns
    0.71
     2018
    0.71
     Joined
    0.69
    06
    0.69
    Act Density 0.155%

    No Known Activations