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

    Neuronpedia

    INDEX
    Explanations

    elements of contrast or comparison in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.59
     the
    -0.52
    ets
    -0.52
     itself
    -0.50
    ord
    -0.50
    mente
    -0.48
     pener
    -0.48
    rion
    -0.48
     around
    -0.47
    ERI
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    1.09
    StructEnd
    1.06
    Vidite
    0.92
    msgTypes
    0.91
    sizeCache
    0.86
     &___
    0.85
    BeginContext
    0.81
    ValueStyle
    0.81
    setVerticalGroup
    0.81
    Demografie
    0.80
    Act Density 0.096%

    No Known Activations