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

    Neuronpedia

    INDEX
    Explanations

    combinations of specific words or phrases related to completion or complementation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to completeness and incompleteness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rad
    -0.68
     inh
    -0.65
     dstg
    -0.64
    è£ħ
    -0.63
    bucks
    -0.63
     Azerb
    -0.61
    beard
    -0.61
    WARD
    -0.61
    IRO
    -0.61
    iewicz
    -0.61
    POSITIVE LOGITS
    teness
    1.58
    mented
    1.29
    mentation
    1.24
     comple
    1.15
    ments
    1.06
    tions
    1.06
    ibilities
    0.95
    etary
    0.92
    rette
    0.90
    ply
    0.88
    Act Density 0.006%

    No Known Activations