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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and superlative forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.09
    3:0.04
    4:0.05
    5:0.09
    6:0.03
    7:0.03
    8:0.34
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     arrang
    -1.81
     disg
    -1.75
    xtap
    -1.75
     disapp
    -1.72
     disag
    -1.71
     hemor
    -1.68
     behavi
    -1.60
    anamo
    -1.56
     sighting
    -1.55
    kef
    -1.55
    POSITIVE LOGITS
    liest
    1.42
    anium
    1.39
    テ
    1.39
    erella
    1.38
    ++++++++
    1.36
     weakest
    1.34
     )]
    1.33
    listed
    1.33
    Uncommon
    1.33
     Belarus
    1.33
    Act Density 0.331%

    No Known Activations