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

    Neuronpedia

    INDEX
    Explanations

    names mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of names and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istar
    -0.79
    yrinth
    -0.77
    romy
    -0.76
    isoft
    -0.71
    psey
    -0.71
    icult
    -0.69
    berra
    -0.69
    yrus
    -0.66
    EMS
    -0.64
    ievers
    -0.62
    POSITIVE LOGITS
    plate
    1.46
    plates
    1.46
    paces
    1.15
     recognition
    0.96
    paced
    0.96
    names
    0.94
    ames
    0.86
     tags
    0.85
    akes
    0.85
     tag
    0.83
    Act Density 0.055%

    No Known Activations