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

    Neuronpedia

    INDEX
    Explanations

    references to algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.85
    :✨
    -0.79
    insics
    -0.66
     Efq
    -0.66
     ſte
    -0.65
    embal
    -0.60
     Anſ
    -0.60
     hollywood
    -0.58
    ſelf
    -0.57
    commodations
    -0.57
    POSITIVE LOGITS
     algorithms
    0.85
     algorithm
    0.85
     Algorithm
    0.68
    algorithms
    0.66
    算法
    0.63
     Pure
    0.61
     algoritmo
    0.60
     algo
    0.60
     pure
    0.60
     Algorithms
    0.58
    Act Density 0.211%

    No Known Activations