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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or courtroom contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.89
    ſelves
    -0.84
     itſelf
    -0.84
     purpoſe
    -0.82
    RenderAtEndOf
    -0.81
     themſelves
    -0.81
     iſt
    -0.80
     houſe
    -0.79
     himſelf
    -0.77
     myſelf
    -0.76
    POSITIVE LOGITS
     '
    0.69
    “
    0.63
     "
    0.62
    UnusedPrivate
    0.59
     ‘
    0.57
     Yes
    0.57
     “
    0.55
    ‘
    0.55
    <td>
    0.54
    ['
    0.54
    Act Density 0.139%

    No Known Activations