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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and petitions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal processes and petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Synopsis
    -0.82
    ivas
    -0.67
    imensional
    -0.66
    word
    -0.66
    ¯¯¯¯¯¯¯¯
    -0.65
    Words
    -0.62
    éĹ
    -0.60
    Contents
    -0.59
    Congratulations
    -0.58
    Appearance
    -0.58
    POSITIVE LOGITS
     another
    0.98
     elsewhere
    0.96
     other
    0.88
     others
    0.86
    etheless
    0.82
     broader
    0.80
     quieter
    0.79
     narrower
    0.78
     hers
    0.78
     whichever
    0.78
    Act Density 0.960%

    No Known Activations