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

    Neuronpedia

    INDEX
    Explanations

    technical details and information, such as software development instructions, system vulnerabilities, and card game strategies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eering
    -0.95
    eers
    -0.90
    eer
    -0.79
    xon
    -0.79
    Downloadha
    -0.78
    croft
    -0.70
     Franch
    -0.70
    mount
    -0.67
    heid
    -0.66
    llan
    -0.62
    POSITIVE LOGITS
    estone
    0.89
    itus
    0.85
    ying
    0.82
    TL
    0.82
    TPS
    0.81
    istics
    0.80
    ues
    0.78
    ipedia
    0.74
    oria
    0.74
    WA
    0.74
    Act Density 0.022%

    No Known Activations