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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring 'rem' followed by a number representing the strength of a change or action

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "remand" in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.87
    gerald
    -0.79
    OPLE
    -0.73
    BOOK
    -0.70
    GY
    -0.69
    gaard
    -0.68
     Petersen
    -0.68
    à¼
    -0.67
    gio
    -0.64
    tips
    -0.64
    POSITIVE LOGITS
    ittance
    1.10
    ilit
    1.09
    ploy
    1.03
    uner
    0.98
    ission
    0.95
    ixed
    0.94
    astered
    0.92
    ixtape
    0.91
     surpr
    0.91
    asters
    0.91
    Act Density 0.004%

    No Known Activations