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

    Neuronpedia

    INDEX
    Explanations

    references to the term "sister" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Demir
    -0.15
    398
    -0.14
    recio
    -0.14
     Alejandro
    -0.14
    ittal
    -0.14
    essim
    -0.14
    rais
    -0.14
    ä»Ķ
    -0.14
    inson
    -0.14
    nat
    -0.14
    POSITIVE LOGITS
    rowsable
    0.17
    uÅŁ
    0.16
    hood
    0.16
    aten
    0.16
    apult
    0.15
    ãĥ«ãĥī
    0.14
     tiá»ĩn
    0.14
    lava
    0.14
    ifes
    0.14
     Blades
    0.13
    Act Density 0.012%

    No Known Activations