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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical quantities or technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of two-party systems and related political terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untled
    -0.75
    SPONSORED
    -0.74
    ename
    -0.73
    reck
    -0.70
    ften
    -0.69
    natureconservancy
    -0.68
    wolves
    -0.66
    REDACTED
    -0.66
    ettel
    -0.66
    PDATE
    -0.65
    POSITIVE LOGITS
    ĪĴ
    0.89
     affair
    0.89
     combo
    0.84
     configurations
    0.84
    imensional
    0.81
     configuration
    0.78
     setups
    0.77
     SLI
    0.73
     mode
    0.69
     occupancy
    0.68
    Act Density 0.129%

    No Known Activations