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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific vocabulary and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.08
     pleaſure
    -1.01
     myſelf
    -1.01
    Personensuche
    -0.98
     Monfieur
    -0.96
     houſe
    -0.96
     Jefus
    -0.95
     themſelves
    -0.93
     ſever
    -0.91
     Chriftian
    -0.90
    POSITIVE LOGITS
     last
    0.56
    hena
    0.55
     u
    0.51
    }}_{\
    0.51
     
    0.51
     er
    0.50
     near
    0.50
    }}_{
    0.50
    past
    0.50
     Bel
    0.50
    Act Density 0.025%

    No Known Activations