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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating capability or function

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.59
     समीक्षाएं
    -0.59
    jspx
    -0.57
    MessageTagHelper
    -0.55
     iParam
    -0.53
    sanity
    -0.53
    ioutil
    -0.50
     Rees
    -0.49
     "..\..\
    -0.46
    swig
    -0.46
    POSITIVE LOGITS
     capable
    0.79
     ſever
    0.79
     @"/
    0.77
     capability
    0.70
     CAPACITY
    0.69
    findpost
    0.69
     Capability
    0.69
     capacity
    0.68
     Capa
    0.68
     againſt
    0.68
    Act Density 0.037%

    No Known Activations