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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.18
     ActionTypes
    -0.16
    æ¯Ķè¾ĥ
    -0.15
     ÎłÎ±Î½
    -0.15
    peg
    -0.14
    ederland
    -0.14
    asil
    -0.14
    wen
    -0.14
    plr
    -0.14
    jak
    -0.14
    POSITIVE LOGITS
     than
    0.39
     then
    0.28
     Than
    0.25
     THAN
    0.24
    _than
    0.20
    Than
    0.20
    than
    0.20
    	then
    0.19
     tan
    0.18
     Then
    0.17
    Act Density 0.127%

    No Known Activations