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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize limitations and scarcity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     both
    -0.81
     zarówno
    -0.75
    both
    -0.71
     både
    -0.69
     sowohl
    -0.67
     also
    -0.67
    BOTH
    -0.66
     zowel
    -0.64
    owohl
    -0.63
     anche
    -0.63
    POSITIVE LOGITS
     handful
    0.67
    而已
    0.64
     limited
    0.62
     marginally
    0.62
     wenige
    0.60
     cursory
    0.60
    limited
    0.59
    Limited
    0.57
     finitely
    0.57
    ほん
    0.55
    Act Density 0.551%

    No Known Activations