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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating large groups or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imagui
    -0.66
     queſta
    -0.65
    <unused52>
    -0.64
    <pad>
    -0.64
    <unused8>
    -0.64
    <unused14>
    -0.64
    <unused21>
    -0.64
    <unused16>
    -0.64
    <unused3>
    -0.63
    <unused17>
    -0.63
    POSITIVE LOGITS
     Many
    1.74
    Many
    1.43
     Most
    1.20
     Some
    1.02
    Most
    0.97
     Muitos
    0.97
     Muchos
    0.96
     Viele
    0.95
     Few
    0.90
     Многие
    0.90
    Act Density 0.126%

    No Known Activations