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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions around perceptions and interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.83
     ftill
    -0.70
     houſe
    -0.65
    первых
    -0.62
     Majefty
    -0.62
     againſt
    -0.61
     fubject
    -0.60
     siguran
    -0.60
     caufe
    -0.59
     ſeveral
    -0.59
    POSITIVE LOGITS
     treated
    0.97
     regarded
    0.93
     treating
    0.88
     viewed
    0.86
     treats
    0.81
     Treated
    0.80
     treat
    0.80
     Treat
    0.74
    treated
    0.73
    treat
    0.73
    Act Density 0.329%

    No Known Activations