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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omin
    -0.16
    igit
    -0.15
    roy
    -0.14
    ispers
    -0.14
    stra
    -0.14
    usz
    -0.14
     Gra
    -0.13
     Kak
    -0.13
    .li
    -0.13
    egas
    -0.13
    POSITIVE LOGITS
    ccione
    0.17
     Rica
    0.16
    inize
    0.15
    nton
    0.15
    auge
    0.15
    lopedia
    0.14
    ().'/
    0.14
     esac
    0.13
    ovich
    0.13
    .throw
    0.13
    Act Density 0.086%

    No Known Activations