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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements related to conflict and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     valide
    -0.57
     houſe
    -0.56
     permittee
    -0.52
    ὴν
    -0.51
     toek
    -0.51
    ganie
    -0.50
     насељу
    -0.49
    PCell
    -0.48
    ABLES
    -0.47
    ITURE
    -0.47
    POSITIVE LOGITS
     noDo
    0.54
    ValueGeneration
    0.52
     spørs
    0.52
     CreateTagHelper
    0.51
    fjspx
    0.51
     betweenstory
    0.51
    zensionen
    0.50
    ArgumentParser
    0.49
    CloseOperation
    0.49
    rungsseite
    0.48
    Act Density 0.292%

    No Known Activations