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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations, projects, or metrics related to planning and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦↵
    -0.19
     [âĢ¦]↵
    -0.17
     &#
    -0.14
     âĢ¦↵
    -0.14
    Âłin
    -0.14
    ...↵
    -0.14
    âĢ¦.
    -0.13
     [âĢ¦
    -0.12
    lessly
    -0.12
    ....↵
    -0.12
    POSITIVE LOGITS
    .scalablytyped
    0.22
    ulario
    0.14
    ÛĮÛĮÙĨ
    0.14
     èĩªåĬ¨çĶŁæĪIJ
    0.13
    огÑĥ
    0.13
     onload
    0.13
    sek
    0.13
    InstantiationException
    0.12
    è¼Ŀ
    0.12
    rotch
    0.12
    Act Density 0.048%

    No Known Activations