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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "rid," particularly in contexts related to removing or eliminating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.73
     ProtoMessage
    -0.67
     Bianca
    -0.61
    PopupWindow
    -0.59
     Dresden
    -0.58
    fonte
    -0.58
     gola
    -0.57
    Maxi
    -0.57
     remotely
    -0.56
     Aiken
    -0.56
    POSITIVE LOGITS
     Rid
    1.10
     rid
    1.02
     hum
    0.94
     Hum
    0.92
    hum
    0.86
    Hum
    0.84
     HUM
    0.79
    ji
    0.79
    \{\\
    0.78
    Rid
    0.77
    Act Density 0.215%

    No Known Activations