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

    Neuronpedia

    INDEX
    Explanations

    references to individuals with inside knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who possess inside information, particularly in the context of trading and industry secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Modest
    -0.72
    {
    -0.69
    cycles
    -0.66
    rome
    -0.65
    ries
    -0.65
    âĶĢ
    -0.63
    bars
    -0.63
    ez
    -0.63
    ridge
    -0.62
    ert
    -0.62
    POSITIVE LOGITS
     insider
    3.82
     insiders
    2.95
     outsider
    2.14
     outsiders
    1.57
     Insider
    1.46
     underdog
    1.24
     whistleblower
    1.24
     Outs
    1.16
     gossip
    1.16
     spoiler
    1.13
    Act Density 0.025%

    No Known Activations