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

    Neuronpedia

    INDEX
    Explanations

    specific dates and temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plr
    -0.17
    bang
    -0.16
    Æł
    -0.15
    esses
    -0.15
    tet
    -0.15
     Morrow
    -0.15
    innen
    -0.14
    rane
    -0.14
    USR
    -0.14
    éĺ¶
    -0.14
    POSITIVE LOGITS
     Favorite
    0.15
    ARGET
    0.14
     ç¯
    0.14
     Bers
    0.14
    favorite
    0.13
     ï
    0.13
    rious
    0.13
     Favorites
    0.13
     perman
    0.13
    inton
    0.13
    Act Density 0.055%

    No Known Activations