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

    Neuronpedia

    INDEX
    Explanations

    words related to properties or statuses, particularly in the context of characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.04
     autorytatywna
    -0.94
    RectangleBorder
    -0.92
     itſelf
    -0.90
     themſelves
    -0.88
     himſelf
    -0.88
     fubject
    -0.87
    )}</
    -0.86
     }</
    -0.85
     purpoſe
    -0.82
    POSITIVE LOGITS
     Non
    0.72
    Non
    0.71
     non
    0.70
    __
    0.64
    非
    0.61
    Sc
    0.59
    ()
    0.58
    non
    0.57
     Sc
    0.56
     met
    0.51
    Act Density 0.185%

    No Known Activations