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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers such as names and dates

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-text token, indicating the conclusion of a relevant section or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theirs
    -0.52
     tradem
    -0.48
     circulation
    -0.46
     embargo
    -0.46
     amnesty
    -0.45
     rushes
    -0.44
    atively
    -0.44
     reper
    -0.44
     abandon
    -0.44
     sovereignty
    -0.43
    POSITIVE LOGITS
    Untitled
    0.95
    Description
    0.92
    Abstract
    0.92
    WASHINGTON
    0.91
    CLOSE
    0.90
    CTV
    0.88
    SAN
    0.84
    Overview
    0.82
    Welcome
    0.82
    Still
    0.79
    Act Density 0.106%

    No Known Activations