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

    Neuronpedia

    INDEX
    Explanations

    instances of decreasing quantities or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ”
    -0.85
     “
    -0.82
     ‘
    -0.79
    “
    -0.79
    .”
    -0.76
    ,”
    -0.75
    dür
    -0.72
    ’
    -0.72
    !”
    -0.70
     (“
    -0.70
    POSITIVE LOGITS
     decrease
    1.37
     Decrease
    1.33
     decreases
    1.27
    Decrease
    1.27
    decre
    1.25
    decrease
    1.25
     Decre
    1.24
     Decreased
    1.21
    Decre
    1.20
     decreased
    1.18
    Act Density 0.182%

    No Known Activations