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

    Neuronpedia

    INDEX
    Explanations

    elements related to geographic or infrastructural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    providedIn
    -0.58
     Waray
    -0.54
     Gött
    -0.54
    فحة
    -0.53
     obsidian
    -0.53
     Maury
    -0.53
     grà
    -0.52
    BeginContext
    -0.51
    Przypisy
    -0.51
    StructEnd
    -0.50
    POSITIVE LOGITS
     Al
    3.27
     al
    3.17
    Al
    2.99
     AL
    2.79
    AL
    2.10
    al
    2.06
     Аль
    1.95
    アル
    1.91
     аль
    1.82
     Ал
    1.76
    Act Density 0.292%

    No Known Activations