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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical formulas and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reatment
    -0.45
     Persson
    -0.41
    Control
    -0.41
    ħ
    -0.40
    Xem
    -0.40
     proced
    -0.40
    ücher
    -0.40
     Aru
    -0.39
    ầng
    -0.39
     handling
    -0.39
    POSITIVE LOGITS
    逆に
    0.87
    Personensuche
    0.81
    0.72
     conversely
    0.71
     pinulongan
    0.71
    Conversely
    0.70
     opposite
    0.70
     Conversely
    0.70
     reverse
    0.70
     Opposite
    0.69
    Act Density 1.122%

    No Known Activations