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

    Neuronpedia

    INDEX
    Explanations

    references to bipartisan efforts or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akit
    -0.15
     restitution
    -0.14
     Mé
    -0.14
    ilde
    -0.14
    -0.14
    bane
    -0.13
    .restaurant
    -0.13
     Salman
    -0.13
     registr
    -0.13
     Mist
    -0.13
    POSITIVE LOGITS
     ninh
    0.17
    lish
    0.17
    Å¡ov
    0.16
    boro
    0.16
    éĩ
    0.15
    ÑĪов
    0.15
    à¥ģà¤Ĺत
    0.15
    744
    0.14
    रल
    0.14
    ishly
    0.14
    Act Density 0.001%

    No Known Activations