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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "finished."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agrega
    -0.72
     lyre
    -0.70
     sobriety
    -0.66
     Escolar
    -0.66
     accrue
    -0.64
     LAX
    -0.62
     firebaseConfig
    -0.61
    ectores
    -0.61
     DMV
    -0.61
     Narod
    -0.61
    POSITIVE LOGITS
     finished
    2.51
     Finished
    2.22
    finished
    2.08
    Finished
    2.00
     completed
    1.72
    FINISHED
    1.56
     Completed
    1.45
    completed
    1.40
    Completed
    1.39
     terminado
    1.24
    Act Density 0.065%

    No Known Activations