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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and metrics used in research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     correctes
    -0.45
    imanapun
    -0.44
    alah
    -0.44
    viu
    -0.41
    <eos>
    -0.41
    didReceive
    -0.41
    Архівовано
    -0.40
     Uang
    -0.39
     vi
    -0.39
     "
    -0.39
    POSITIVE LOGITS
     للاسماء
    1.03
    
    0.92
     CreateTagHelper
    0.83
     kasarigan
    0.82
    Carriera
    0.82
    ToBounds
    0.79
    ReusableCell
    0.76
    rungsseite
    0.76
    GEBURTS
    0.75
     שוליים
    0.73
    Act Density 0.252%

    No Known Activations