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

    Neuronpedia

    INDEX
    Explanations

    technology-related terms related to power sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to power sources or the concept of being powered

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.81
    ordan
    -0.78
    edi
    -0.77
    ylum
    -0.69
     ç¥ŀ
    -0.68
     Debor
    -0.68
    innon
    -0.68
    roma
    -0.67
    asper
    -0.66
    myra
    -0.65
    POSITIVE LOGITS
     powered
    0.89
    wagen
    0.79
     outage
    0.74
     Powered
    0.73
     wheelchair
    0.72
    powered
    0.71
     propelled
    0.70
     powering
    0.70
    escape
    0.69
    undai
    0.68
    Act Density 0.014%

    No Known Activations