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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebek
    -0.18
    ÑĤеÑĢн
    -0.16
     klu
    -0.15
    lew
    -0.14
    opian
    -0.13
    zia
    -0.13
    /mit
    -0.13
    elist
    -0.13
     è
    -0.13
    _VO
    -0.13
    POSITIVE LOGITS
     Merrill
    0.14
     chin
    0.14
     Rin
    0.14
     Shi
    0.14
    âĢ¦↵
    0.13
    ti
    0.13
    ties
    0.13
     Burgess
    0.13
     Allison
    0.13
     Bend
    0.13
    Act Density 0.142%

    No Known Activations