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

    Neuronpedia

    INDEX
    Explanations

    words related to naming conventions or identifiers in programming or technology contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to 'name' in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -0.97
    elaide
    -0.87
    ilib
    -0.78
    psey
    -0.76
    irth
    -0.75
    EMS
    -0.74
    romy
    -0.73
    icult
    -0.73
    emonium
    -0.71
    awaru
    -0.69
    POSITIVE LOGITS
    plates
    1.33
    plate
    1.18
    paces
    1.13
    names
    0.91
    brand
    0.84
    ames
    0.84
    paced
    0.83
    mark
    0.79
     names
    0.79
    cloth
    0.79
    Act Density 0.039%

    No Known Activations