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

    Neuronpedia

    INDEX
    Explanations

    phrases related to representation and significance in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Higgins
    -0.16
    Thumb
    -0.15
    ombo
    -0.14
    edb
    -0.14
    uzzer
    -0.14
    atile
    -0.14
    ikat
    -0.13
    olist
    -0.13
    oter
    -0.13
    aeper
    -0.13
    POSITIVE LOGITS
    ingle
    0.17
     Campos
    0.16
     main
    0.15
    vÃŃ
    0.15
    789
    0.15
     key
    0.14
    578
    0.14
     occasions
    0.14
    ãģĤãģĴ
    0.14
    asics
    0.14
    Act Density 0.005%

    No Known Activations