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

    Neuronpedia

    INDEX
    Explanations

    promotional phrases and calls to action in a text

    oai_token-act-pair · gpt-3.5-turbo

    elements related to promotional events or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outwe
    -0.73
    xual
    -0.73
     outweigh
    -0.70
     bullies
    -0.65
    ilibrium
    -0.63
     vacc
    -0.63
     authoritarian
    -0.63
     influences
    -0.63
     undecided
    -0.62
     corpor
    -0.61
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.10
    ³³³
    1.03
    ³³
    0.98
    ³³³³³³³³
    0.94
    October
    0.91
    ³³³³
    0.90
    minster
    0.90
    December
    0.90
    Includes
    0.90
    Overview
    0.89
    Act Density 0.365%

    No Known Activations