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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates and significant historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     if
    -1.01
    Давайте
    -0.87
     Jeśli
    -0.79
    Abbiamo
    -0.73
    Если
    -0.73
     hvis
    -0.73
     jeśli
    -0.72
    If
    -0.70
     अगर
    -0.70
     اگه
    -0.69
    POSITIVE LOGITS
     Shortly
    1.05
     Following
    1.01
    Shortly
    0.98
     During
    0.92
     Between
    0.92
     In
    0.92
    Following
    0.90
     Subsequently
    0.83
    Between
    0.83
     Later
    0.83
    Act Density 0.642%

    No Known Activations