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

    Neuronpedia

    INDEX
    Explanations

    mentions of reports or news

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reports."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wedge
    -0.74
    othing
    -0.70
    egal
    -0.68
     Klux
    -0.67
    actic
    -0.65
    asus
    -0.64
     sympath
    -0.62
    oan
    -0.62
     Sabha
    -0.61
    ococ
    -0.61
    POSITIVE LOGITS
     reports
    0.96
    reports
    0.85
    books
    0.80
    ynthesis
    0.76
     Reports
    0.75
    Reporting
    0.75
    flows
    0.73
    etter
    0.73
    udo
    0.72
    uggest
    0.71
    Act Density 0.027%

    No Known Activations