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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hoped, knew, pictured, expected, imagined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Volkes
    -0.46
     bordir
    -0.44
     bowiem
    -0.41
     Grüsse
    -0.41
     Kerja
    -0.39
     aihe
    -0.38
     inderdaad
    -0.37
     fotográfica
    -0.37
     hyö
    -0.37
     damska
    -0.37
    POSITIVE LOGITS
    IntoConstraints
    0.69
    :✨
    0.60
     expectations
    0.54
    RTHOOK
    0.53
     wished
    0.53
    AsUp
    0.52
     expected
    0.50
     desired
    0.49
     requestCode
    0.49
     hoped
    0.49
    Act Density 0.028%

    No Known Activations