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

    Neuronpedia

    INDEX
    Explanations

    words related to electricity and currents

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electrical currents and current flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.90
    amy
    -0.88
    ËĪ
    -0.84
     Bei
    -0.79
    earth
    -0.79
    oru
    -0.77
    aths
    -0.76
    ever
    -0.75
    omy
    -0.73
    alty
    -0.73
    POSITIVE LOGITS
     flowing
    0.78
    drawn
    0.70
    onductor
    0.69
     generation
    0.67
     iteration
    0.66
     incarnation
    0.64
     flows
    0.63
     Register
    0.61
    ¶
    0.61
     circulating
    0.61
    Act Density 0.024%

    No Known Activations