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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors indicating variations in quality or condition

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

    followed by descriptive attributes

    np_acts-logits-general · gemini-2.0-flash

    adjectives often followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crutches
    -0.82
     eigenvectors
    -0.81
     multiples
    -0.80
     sachets
    -0.78
     diagonals
    -0.77
     swabs
    -0.77
     dignité
    -0.76
     invariants
    -0.76
     bonté
    -0.76
     chandeliers
    -0.75
    POSITIVE LOGITS
     series
    0.60
     version
    0.60
    makeText
    0.59
     IBOutlet
    0.56
     vaisseaux
    0.56
     quantités
    0.52
     }}"></
    0.52
     mixture
    0.51
     intérêts
    0.51
     few
    0.50
    Act Density 1.603%

    No Known Activations