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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a downward movement or descent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Viki
    -0.97
     Magi
    -0.94
     belangrij
    -0.84
    érêt
    -0.83
    ształ
    -0.80
     Winaray
    -0.79
    ⅰ
    -0.79
    licet
    -0.79
    PhysRev
    -0.79
    tershire
    -0.78
    POSITIVE LOGITS
     down
    1.87
     Down
    1.79
    Down
    1.75
     DOWN
    1.69
    down
    1.61
    DOWN
    1.56
    downs
    1.50
    Downs
    1.38
     downs
    1.36
     Downs
    1.27
    Act Density 0.089%

    No Known Activations