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

    Neuronpedia

    INDEX
    Explanations

    words related to objects with flat surfaces, often used for various purposes like writing, gaming, or medical applications

    oai_token-act-pair · gpt-3.5-turbo

    references to protective gear or padding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AME
    -0.80
    Marx
    -0.71
     Allies
    -0.69
    vous
    -0.67
    heid
    -0.67
     Relations
    -0.65
    ews
    -0.65
    llor
    -0.64
     Marxist
    -0.64
     Zombies
    -0.64
    POSITIVE LOGITS
     pad
    1.39
     pads
    1.21
    pad
    1.09
    bed
    0.91
    awan
    0.90
    caps
    0.86
    daq
    0.83
    rice
    0.83
    pole
    0.81
    lock
    0.77
    Act Density 0.007%

    No Known Activations