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

    Neuronpedia

    INDEX
    Explanations

    words related to legal matters or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal issues and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cale
    -0.82
    rower
    -0.68
    creen
    -0.66
    ensor
    -0.64
     Tribunal
    -0.63
    erver
    -0.62
    itute
    -0.61
    ervative
    -0.60
    ource
    -0.60
    itcher
    -0.59
    POSITIVE LOGITS
    lets
    0.82
    loads
    0.80
    cules
    0.80
     fragments
    0.77
    goers
    0.76
     #
    0.74
     proportions
    0.74
     lengths
    0.73
    houses
    0.72
    ologies
    0.72
    Act Density 0.585%

    No Known Activations