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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.71
     Efq
    -0.64
     myſelf
    -0.63
     detuvo
    -0.61
     transférez
    -0.58
     }}$}
    -0.58
     Chwiliwch
    -0.58
    DebuggerStep
    -0.57
    mités
    -0.57
     themſelves
    -0.57
    POSITIVE LOGITS
     duck
    0.58
    تقاوى
    0.57
    ware
    0.56
     chi
    0.56
     damn
    0.56
    ste
    0.56
     Damn
    0.55
    VARD
    0.55
    chi
    0.54
     darn
    0.54
    Act Density 2.616%

    No Known Activations