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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters used in listings or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agina
    -0.19
    mall
    -0.15
    idir
    -0.15
    ilee
    -0.15
    oki
    -0.14
    rost
    -0.14
     lon
    -0.13
    vert
    -0.13
    antry
    -0.13
     Whe
    -0.13
    POSITIVE LOGITS
    anner
    0.14
    akov
    0.14
    curacy
    0.14
     Duo
    0.14
     hete
    0.14
    одав
    0.14
    wiÄħ
    0.14
    خرج
    0.14
    steller
    0.14
    arium
    0.13
    Act Density 0.002%

    No Known Activations