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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss conditions or rules related to terms of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.14
     transfieras
    -1.10
     ſeveral
    -1.08
     ſever
    -1.07
    ✨:
    -1.05
     fevere
    -1.00
     bershka
    -0.99
     houſe
    -0.99
     Monfieur
    -0.98
     Theſe
    -0.97
    POSITIVE LOGITS
     متعلقه
    0.60
    tesy
    0.60
     través
    0.56
    μφωνα
    0.54
    Acerca
    0.54
     através
    0.53
    仗
    0.52
    glColor
    0.50
     Senhora
    0.50
     adap
    0.50
    Act Density 0.217%

    No Known Activations