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

    Neuronpedia

    INDEX
    Explanations

    sections of text that are titles or headings within the document

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to articles and topics under discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiveness
    -0.60
    azeera
    -0.57
    miss
    -0.56
     reserves
    -0.55
     forg
    -0.54
    etimes
    -0.54
    "],"
    -0.52
     sinks
    -0.52
    ])
    -0.51
    alus
    -0.49
    POSITIVE LOGITS
     gist
    0.70
     acronym
    0.69
     premise
    0.67
     comprised
    0.62
     consisted
    0.58
     hatched
    0.57
    ccording
    0.56
     loosely
    0.56
    vertisement
    0.55
     "âĢ¦
    0.55
    Act Density 1.623%

    No Known Activations