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

    Neuronpedia

    INDEX
    Explanations

    connectors and prepositions that establish relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoa
    -0.16
    uren
    -0.15
    onde
    -0.15
     Rockies
    -0.15
    ollen
    -0.15
    odzi
    -0.14
    èªī
    -0.14
     Mez
    -0.14
    TREE
    -0.14
    rs
    -0.14
    POSITIVE LOGITS
    stad
    0.16
    yat
    0.15
    nard
    0.15
     sna
    0.15
    budget
    0.14
    iná
    0.14
    ä¸įçŁ¥
    0.13
    edException
    0.13
    Ñĸнки
    0.13
    ledge
    0.13
    Act Density 0.003%

    No Known Activations