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

    Neuronpedia

    INDEX
    Explanations

    words related to instructional or informational guides

    oai_token-act-pair · gpt-3.5-turbo

    titles of guides and analytical reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forfe
    -0.67
    bucks
    -0.67
     cancell
    -0.67
    OOOO
    -0.66
    umers
    -0.65
     tether
    -0.65
    etsu
    -0.63
     isEnabled
    -0.63
     hook
    -0.63
     chops
    -0.63
    POSITIVE LOGITS
     Retrieved
    1.05
     Edited
    0.84
     Historical
    0.82
     1914
    0.74
     Archive
    0.73
     Contemporary
    0.72
     edited
    0.70
    rift
    0.70
     1961
    0.70
     1951
    0.69
    Act Density 0.727%

    No Known Activations