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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or actions involving countries and political situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ."[
    -0.83
     thereof
    -0.81
    Zip
    -0.79
    .[
    -0.75
    ).[
    -0.71
    Doc
    -0.70
     [&
    -0.69
     somet
    -0.68
    natureconservancy
    -0.68
    ".[
    -0.67
    POSITIVE LOGITS
     controvers
    1.04
     criticised
    0.92
     accused
    0.92
     accuse
    0.86
     sacked
    0.81
     embroiled
    0.80
     notoriously
    0.77
     accuses
    0.77
     famously
    0.76
     ousted
    0.75
    Act Density 1.050%

    No Known Activations