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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its frequency in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inSlope
    -0.56
     ―――――
    -0.54
    RTGC
    -0.54
    aragus
    -0.53
     AssemblyCompany
    -0.50
    ArgumentParser
    -0.49
    riterion
    -0.49
     TextInputType
    -0.48
    AISSEE
    -0.48
     xhr
    -0.48
    POSITIVE LOGITS
     thats
    0.82
     they
    0.81
     it
    0.73
     we
    0.67
    they
    0.65
    thats
    0.65
     there
    0.64
    nothing
    0.64
     inilah
    0.63
    there
    0.60
    Act Density 0.709%

    No Known Activations