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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to specific fields or concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to appropriate standards, measures, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.83
    famous
    -0.77
    pora
    -0.74
    psey
    -0.66
     thunder
    -0.65
    urat
    -0.64
     furiously
    -0.64
    noxious
    -0.63
     infamous
    -0.63
    inged
    -0.61
    POSITIVE LOGITS
    TEXTURE
    0.75
    RF
    0.74
    Applic
    0.73
    ãĤ®
    0.72
    VALUE
    0.72
    worthiness
    0.72
    ADVERTISEMENT
    0.70
     alloc
    0.70
    ãĤ¢ãĥ«
    0.69
    Stock
    0.67
    Act Density 0.456%

    No Known Activations