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

    Neuronpedia

    INDEX
    Explanations

    references to specific academic citations or authors in scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynos
    -0.16
    elles
    -0.15
    Formatting
    -0.15
    ¹Ħ
    -0.14
    alc
    -0.14
    meyen
    -0.14
    utsche
    -0.14
    olest
    -0.13
    abay
    -0.13
    alcon
    -0.13
    POSITIVE LOGITS
    201
    0.25
     et
    0.19
    202
    0.14
    .github
    0.14
    200
    0.13
    etal
    0.13
    زش
    0.13
     &↵
    0.12
     _
    0.12
     paper
    0.12
    Act Density 0.015%

    No Known Activations