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

    Neuronpedia

    INDEX
    Explanations

    excerpts or quotes from documents

    oai_token-act-pair · gpt-3.5-turbo

    references to excerpts or passages from documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ggle
    -1.05
    thood
    -0.84
    gaard
    -0.80
    ggles
    -0.77
    mos
    -0.73
    LD
    -0.69
    ¯¯¯¯
    -0.68
    ceans
    -0.68
    uay
    -0.67
    STD
    -0.67
    POSITIVE LOGITS
     excerpts
    1.14
     excerpt
    1.06
     snippets
    1.02
     redacted
    0.85
    cerpt
    0.85
     guiActiveUn
    0.82
    aneous
    0.80
     quotes
    0.79
    aneously
    0.77
     summar
    0.77
    Act Density 0.021%

    No Known Activations