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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly percentages and statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.18
    ùy
    -0.16
    olec
    -0.15
    tae
    -0.15
    obao
    -0.14
     Gins
    -0.14
     prim
    -0.14
     cha
    -0.14
     Cypress
    -0.14
     stake
    -0.14
    POSITIVE LOGITS
    ALER
    0.15
    .syntax
    0.15
    .spin
    0.14
    enÄĽ
    0.14
    .Inject
    0.13
    aper
    0.13
     Marks
    0.13
    -Cs
    0.13
     Morr
    0.13
    Descriptors
    0.12
    Act Density 0.104%

    No Known Activations