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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and expressions that indicate various powers and indices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑı
    -0.17
    ries
    -0.17
    arna
    -0.15
    ftware
    -0.15
    recio
    -0.15
    iris
    -0.15
    mán
    -0.14
    OrUpdate
    -0.14
    baugh
    -0.14
    ERSIST
    -0.14
    POSITIVE LOGITS
    prime
    0.17
    anted
    0.17
     prim
    0.16
    akin
    0.15
    assin
    0.15
    SCI
    0.15
    CTSTR
    0.14
     prime
    0.14
     primer
    0.14
    ozy
    0.14
    Act Density 0.066%

    No Known Activations