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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or elements from a structured data context, particularly related to nodes and values in a graph or tree-like structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Third
    -1.32
    Third
    -1.19
     third
    -1.17
     thirds
    -1.14
     Thirdly
    -1.13
    3
    -1.10
    third
    -1.09
     Drittel
    -1.08
     III
    -1.08
    thirds
    -1.05
    POSITIVE LOGITS
    kuti
    0.48
     Biv
    0.47
     cellspacing
    0.46
    AfterEach
    0.45
     quarts
    0.45
     Horacio
    0.45
    Clik
    0.44
     Jungen
    0.44
     Junge
    0.44
    belline
    0.43
    Act Density 0.801%

    No Known Activations