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

    Neuronpedia

    INDEX
    Explanations

    sentences that introduce or provide context for information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    orrhea
    -0.65
    ↵↵
    -0.60
    ğim
    -0.56
    RegressionTest
    -0.55
     marginLeft
    -0.52
     mitään
    -0.52
    évaluateur
    -0.51
     vecka
    -0.51
    unier
    -0.51
    imedes
    -0.51
    POSITIVE LOGITS
    ValueStyle
    0.75
    extAlignment
    0.75
     disambiguazione
    0.73
    PositiveButton
    0.66
    afficheront
    0.65
    HasMaxLength
    0.59
    \}\\
    0.59
    NegativeButton
    0.58
     تضيفلها
    0.57
    Sucesor
    0.56
    Act Density 0.029%

    No Known Activations