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

    Neuronpedia

    INDEX
    Explanations

    URLs and references to online news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ired
    -0.16
    еÑĪ
    -0.14
    abras
    -0.14
    ibar
    -0.14
    ãĥ¼ãĥ
    -0.14
    pone
    -0.13
    меÑĪ
    -0.13
    ppers
    -0.13
     Affero
    -0.13
     yet
    -0.12
    POSITIVE LOGITS
     Bent
    0.17
     EntityState
    0.16
    ãģ£ãģ¡
    0.15
    /TT
    0.15
    .ua
    0.15
    erea
    0.14
    ÎŃÏģα
    0.14
    ربÙĬØ©
    0.14
    fft
    0.14
    ILON
    0.14
    Act Density 0.006%

    No Known Activations