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

    Neuronpedia

    INDEX
    Explanations

    elements related to scientific research and academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leigh
    -0.16
    oute
    -0.16
    heim
    -0.15
    wald
    -0.15
     Sas
    -0.15
    ammed
    -0.15
     Lar
    -0.14
     oby
    -0.14
    á
    -0.14
     Cass
    -0.13
    POSITIVE LOGITS
     demonstr
    0.18
    adera
    0.17
     modification
    0.16
    ÑĩÑĥк
    0.16
    hong
    0.15
    862
    0.15
     Modification
    0.15
    Modification
    0.15
     Trie
    0.15
     Maz
    0.15
    Act Density 0.029%

    No Known Activations