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

    Neuronpedia

    INDEX
    Explanations

    phrases quantifying small amounts or numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gameserver
    -0.77
     doInBackground
    -0.75
    openConnection
    -0.74
     wikipagina
    -0.73
     ProtoMessage
    -0.73
    DockStyle
    -0.71
    KURZBESCHREIBUNG
    -0.71
     MessageBoxIcon
    -0.70
    UseVisualStyle
    -0.68
     isSet
    -0.67
    POSITIVE LOGITS
     some
    0.91
     bunch
    0.79
     alguns
    0.75
     algunos
    0.74
    some
    0.74
     algunas
    0.73
     several
    0.73
     quelques
    0.72
     qualche
    0.70
     dozen
    0.70
    Act Density 0.117%

    No Known Activations