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

    Neuronpedia

    INDEX
    Explanations

    references to premium and high-quality content

    oai_token-act-pair · gpt-3.5-turbo

    references to digital content and its distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siem
    -0.67
     Sons
    -0.67
    athan
    -0.66
    rolet
    -0.66
    udeb
    -0.65
    vals
    -0.65
    obil
    -0.63
     Cot
    -0.63
     damn
    -0.62
    dinand
    -0.59
    POSITIVE LOGITS
    edly
    1.29
     content
    0.92
     creators
    0.89
    Content
    0.83
     creator
    0.74
     Content
    0.73
    eval
    0.71
    iar
    0.70
    content
    0.69
     snippets
    0.69
    Act Density 0.029%

    No Known Activations