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

    Neuronpedia

    INDEX
    Explanations

    specific political references related to character names, places, and legislative terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    StoreMessageInfo
    -0.61
     Infórmanos
    -0.54
    Према
    -0.53
    idać
    -0.52
     fallu
    -0.52
     vín
    -0.52
    redients
    -0.51
     Kidd
    -0.51
    toLocale
    -0.51
     perſon
    -0.51
    POSITIVE LOGITS
    WebControls
    0.72
    原始内容存档于
    0.67
     CYTHON
    0.57
    Plz
    0.57
    #
    0.56
     faim
    0.56
    ArgumentParser
    0.54
    illerato
    0.54
    CharStream
    0.54
    ukah
    0.53
    Act Density 0.000%

    No Known Activations