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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a lack of quantity or minimal presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wings
    -0.60
     ComVisible
    -0.52
    <0x90>
    -0.50
    lıyor
    -0.50
    <eos>
    -0.50
    H
    -0.50
    ρχ
    -0.49
     Royal
    -0.49
    ectoria
    -0.49
    onav
    -0.49
    POSITIVE LOGITS
     Few
    0.92
    Few
    0.90
     Rarely
    0.84
     seldom
    0.83
     rarely
    0.82
     FEW
    0.80
     guère
    0.79
     Hardly
    0.79
     hardly
    0.77
     leſs
    0.76
    Act Density 0.170%

    No Known Activations