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

    Neuronpedia

    INDEX
    Explanations

    references to articles and their associated DOIs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hart
    -0.16
    ume
    -0.15
    athy
    -0.15
    инкÑĥ
    -0.15
    .AddParameter
    -0.15
    isia
    -0.14
    ville
    -0.14
    hip
    -0.14
    alte
    -0.14
     Xuân
    -0.14
    POSITIVE LOGITS
    CESS
    0.15
    ghost
    0.15
    Looper
    0.15
    888
    0.14
    ois
    0.14
    VOKE
    0.13
    oft
    0.13
    .nt
    0.13
    esis
    0.13
    ĶåĽŀ
    0.13
    Act Density 0.029%

    No Known Activations