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

    Neuronpedia

    INDEX
    Explanations

    phrases related to confirmation and registration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.76
    MigrationBuilder
    -0.75
     ſtate
    -0.72
     houſe
    -0.71
     pleaſure
    -0.70
    
    -0.70
     whofe
    -0.70
    transQ
    -0.69
    StatusOK
    -0.68
     ftate
    -0.68
    POSITIVE LOGITS
    brar
    0.42
    ти
    0.41
    gdx
    0.40
    ificar
    0.40
    FieldBuilder
    0.39
    cipar
    0.38
    álni
    0.37
    ть
    0.37
    żd
    0.37
    íteni
    0.36
    Act Density 0.066%

    No Known Activations