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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and security, particularly focusing on browsing protection and key systems

    oai_token-act-pair · gpt-3.5-turbo

    references to electronic or digital interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     denomin
    -0.54
     prest
    -0.52
     predec
    -0.51
     supplemented
    -0.51
     Moroc
    -0.49
     incorpor
    -0.49
     opio
    -0.47
     latter
    -0.46
     exerc
    -0.46
     eventual
    -0.46
    POSITIVE LOGITS
     onto
    0.69
     into
    0.57
     differently
    0.55
    phies
    0.53
    marks
    0.51
    netflix
    0.50
    coins
    0.50
    >(
    0.50
    RNA
    0.49
    ARS
    0.49
    Act Density 0.881%

    No Known Activations